ultragoal
Skill4 starsChanged todayMITView on GitHub
[oh-my-agy] Create and execute durable repo-native multi-goal plans with a goals.json + ledger.jsonl audit trail, sequential completion, review gates, and resume. Use for $ultragoal, 'create-goals', 'complete-goals', durable multi-goal execution, or the Autopilot execution stage.
8 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 9, 2026
- Joonghyun-Lee-Frieren/oh-my-antigravitytheir own version, first seen Oct 25, 2026
- Gopyr/gopyr-skills-hubtheir own version, first seen Oct 11, 2026
- Joonghyun-Lee-Frieren/oh-my-gemini-clitheir own version, first seen Oct 8, 2026
- Yeachan-Heo/oh-my-claude-sisyphustheir own version, first seen Oct 8, 2026
- Yeachan-Heo/oh-my-codexedited, first seen Oct 8, 2026
Used with
Projects with it also use execute, map and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
sahinSkillexecute
Also in 4 projects that use this
AWSSkillmap
Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.
Also in 3 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 5 projects that use this
genomewalkerSkilllearn
Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- Yeachan-Heo/oh-my-codex★ 34k10% same
Wrote their own version · 7
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- huytieu/COG-second-brain★ 1.3ksame name
- Joonghyun-Lee-Frieren/oh-my-antigravity★ 214same name
- Joonghyun-Lee-Frieren/oh-my-gemini-cli★ 214same name
- Nexus-Organization-Infosec/ClaudeSkills★ 1same name
- Gopyr/gopyr-skills-hub★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- rules/AGENTS.mdAGENTS.md
- ai-slop-cleanerSkill
- analyzeSkill
- askSkill
- autopilotSkill
- cancelSkill
- code-reviewSkill
- deep-interviewSkill
- deep-researchSkill
- doctorSkill
- hudSkill
- loftSkill
- modernizeSkill
- performance-goalSkill
- prSkill
- ralplanSkill
- releaseSkill
- skillSkill
- teamSkill
- threat-modelSkill
- ultraqaSkill
- visual-ralphSkill
- wikiSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 1 is distinctive, and 10 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use for $ultragoal, create-goals, complete-goals, durable multi-goal planning, or sequential execution of an approved plan/spec.
- Very specific: line 60
Read the brief: the deep-interview spec, ralplan PRD/test-spec, or the user's inline brief.
- Very specific: line 62
Write goals.json, append created ledger entries, and show the user a compact goal table (plus oh-my-agy HUD once if the HUD sidecar is …
- Very specific: line 68
Ralplan receipt verification: when entering from $ralplan (.omagy/plans/prd-<slug>.md + .omagy/plans/ralplan-review-<slug>.json), run
- Very specific: line 69
Stash-free shadow checkpoints: before risky multi-file edits or migrations, snapshot working-tree, .git/index, and untracked state via sh …
- Very specific: line 97
If verification fails with failure_class: "harness" (test runner setup, missing fixture, port/env glitch), run up to 1 bounded …
- Very specific: line 112
Before final completion (phase reviewing):
- Distinctive: line 114
Run targeted verification for every goal.
- Very specific: line 115
Run $ai-slop-cleaner on the changed files, then rerun verification.
- Very specific: line 117
Run $code-review through independent code-reviewer and architect subagent lanes.
- Very specific: line 118
When clean: append a final-gate ledger entry with cleaner, verification, review, and invariant evidence.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ultragoal Workflow
When to use
Use for $ultragoal, create-goals, complete-goals, durable multi-goal planning, or sequential execution of an approved plan/spec. Also used as Autopilot's execution stage.
The repo ledger is the single source of truth. Antigravity's /goal slash command is user-triggered. You may suggest it for very long runs, but never depend on it.
Durable artifacts (leader-owned)
.omagy/ultragoal/brief.md: the source brief (spec or plan text, or a pointer to it)..omagy/ultragoal/goals.json: the plan..omagy/ultragoal/ledger.jsonl: append-only audit trail, one JSON object per line..omagy/ultragoal/notepad.md: compaction-resilient working memory organized under## Priority,## Working, and## Manualheadings (omagy-hook.mjsauto-reinjects exported sections up to2,000chars after<CONTEXT_SUMMARY>compaction so critical invariants, rulings, and live context survive compaction).
goals.json schema:
{
"version": 1,
"criteria_revision": 1,
"objective": "<one-line aggregate objective>",
"source": ".omagy/specs/deep-interview-<slug>.md | .omagy/plans/prd-<slug>.md | inline",
"created_at": "<ISO>",
"updated_at": "<ISO>",
"invariants": ["<architecture/domain invariant that must hold at the end>"],
"goals": [
{
"id": "G1",
"title": "<short title>",
"objective": "<verifiable objective>",
"rigor": "light|heavy",
"acceptance": ["<testable criterion>"],
"status": "pending|in_progress|complete|blocked|failed|superseded",
"depends_on": [],
"product_failures": 0,
"evidence": null
}
]
}Goal rigor classification (rigor):
"light": narrow change inside an existing module/pattern with no schema, auth, security, or public API contract change. Verified by targeted tests + acceptance check."heavy": cross-cutting change, new boundary/schema/auth/security surface, or state machine change. Requires targeted tests + at least 1 adversarial probe + independentverifier(AdversarialVerify) check before checkpointing.
Ledger entry shape (append; never rewrite earlier lines):
{"at":"<ISO>","goal_id":"G1","event":"created|started|checkpoint|blocked|failed|steer|review-blockers|final-gate","status":"<status>","evidence":"<commands + exit codes / file refs>","note":"<optional>"}Append a ledger line using the crash-resilient newline-isolated hook helper (sh <plugin>/hooks/run.sh append-jsonl .omagy/ultragoal/ledger.jsonl '<json>', which prepends \n if a prior crash left a torn tail and refuses symlinks), or by reading the file and writing it back with the new line added on its own newline. Read the ledger tolerantly (sh <plugin>/hooks/run.sh read-jsonl .omagy/ultragoal/ledger.jsonl or line-by-line JSON parsing that skips malformed torn lines).
Operational steps: create
- Read the brief: the deep-interview spec, ralplan PRD/test-spec, or the user's inline brief. Copy it or point to it from
brief.md. - Decompose it into right-sized, independently verifiable vertical feature slices (using a
Contract-Firstfoundational goal before parallel$teamfan-out and aRisk-Firstspike goal for existential technical unknowns) with testable acceptance criteria and explicit dependencies. Split any candidate goal touching> 5–8files, spanning>= 2independent subsystems, or joining two independent behaviors with"and"in itstitle. Carry spec non-goals,Always / Ask First / Neverdecision boundaries, and invariants intogoals.json. - Write
goals.json, appendcreatedledger entries, and show the user a compact goal table (plus[oh-my-agy HUD](sidecar://oh-my-agy/hud/)once if the HUD sidecar is enabled). - Standalone: write
.omagy/state/ultragoal-state.json(mode:"ultragoal",active:true,current_phase:"planning"). Inside Autopilot: keep the Autopilot state and set itscurrent_phase:"ultragoal".
Operational steps: execute
- Pre-Flight Receipt Check, Shadow Checkpoints & Scoped Per-Goal Staging:
- Ralplan receipt verification: when entering from
$ralplan(.omagy/plans/prd-<slug>.md+.omagy/plans/ralplan-review-<slug>.json), runsh <plugin>/hooks/run.sh plan-hash verify .omagy/plans/prd-<slug>.md .omagy/plans/ralplan-review-<slug>.json --jsonfirst (exitCode: 0required; halt if the PRD/test-spec drifted after approval or contains fake-timeline violations unless re-approved or steered). - Stash-free shadow checkpoints: before risky multi-file edits or migrations, snapshot working-tree,
.git/index, and untracked state viash <plugin>/hooks/run.sh checkpoint create <goal-id> --json(refs/omagy/checkpoints/<id>, keepinggit stash listempty andHEADunchanged); roll back cleanly on failed experiments viash <plugin>/hooks/run.sh checkpoint rollback <id> --json. - Dirty-worktree baseline & scoped staging: capture
git status --porcelainbefore starting so pre-existing modified/untracked files stay untouched. Whenever creating per-goal commits, never run blindgit add -A,git add ., orgit commit -a: stage explicit goal-owned paths only (git add -- <owned-paths>) and verify staged files viagit diff --staged --name-onlyso pre-existing dirty files,.omagy/scratch state, and secrets never stage.
- Ralplan receipt verification: when entering from
Repeat until every goal is complete (or superseded):
- Pick the first
pendinggoal whose dependencies are complete. Set itin_progress, appendstarted, and set the phase toexecuting. - Implement the goal: solo, or via an
executorsubagent for a bounded slice, or via$teamwhen parallel lanes are justified.- Zero-Context-Bleed Brief & Review Handoffs: extract per-goal briefs via
sh <plugin>/hooks/run.sh goal-brief .omagy/ultragoal/goals.json <goal_id>and package commit ranges viash <plugin>/hooks/run.sh review-package <workspace> <base_sha> <head_sha>so subagents read file paths instead of inline prompt dumps. - 4-State Worker Routing & Model Escalation: handle worker returns deterministically (and harvest any
### Noticed (Out of Scope)items into"Rulings made & Deferred minors"without scope-creeping the active goal):COMPLETED: proceed to step 3 verification.COMPLETED_WITH_CONCERNS: inspect the reported concern (e.g., file growth or fragile edge case); either log aRuling:(event:"steer",kind:"ruling") withcost_if_wrongor run a targeted fix pass before checkpointing.NEEDS_CONTEXT: if a signature/path is missing or the worker reports a spec-vs-codebase architecture contradiction (file:linefalsification), supply the authoritative context viasend_messageto the same worker conversation ID (or record an explicitsteer/ escalate when the spec contract itself is contradicted) without incrementingproduct_failures.BLOCKED: if a worker onModel: "flash"or"inherit"stalls after 2 attempts on a complex implementation slice, escalate the retry to a higher model tier (flash -> inherit -> pro).
- Zero-Context-Bleed Brief & Review Handoffs: extract per-goal briefs via
- Audit the goal against real artifacts (
current_phase:"verifying"):- Apply the No-Reassurance Test Rerun Rule: never re-run an unchanged passing test command when zero files have been edited since that pass.
- For
"rigor": "light", run targeted tests and acceptance checks directly. - For
"rigor": "heavy", record the leader's internalDoneClaim(changed files, commands + exit codes, criterion mapping, and canonicalverdictfromVERIFICATION_VERDICTS:live-ui-verified | unit-test-verified | type-check-only | enforcement-verified | formally-verified | verifier-blocked | verifier-failed), then validate via theverifiersubagent (AdversarialVerify) using a Blind-Claim Packet:- Blind-Claim
AdversarialVerifyInput Rule: pass onlyARTIFACT(actual diff /review-packagepath / touched file paths) +CONTRACT(verbatim goalacceptancecriteria,goals.jsoninvariants, andConsumes / Producessignatures) + raw command exit codes and diagnostic outputs—stripping persuasive executor narrative summaries (CLAIMself-assessments or prose rationales explaining why code is "safe"). AdversarialVerifyreturnsverdict:"confirmed" | "false-positive" | "needs-fix" | "needs-human-review"andfailure_class:"none" | "product" | "harness".
- Blind-Claim
- 4-Tier
RECONCILEPrecedence: classify every verification discrepancy, adversarial probe hit, or review finding in strict top-down precedence order:(1) Contract gap— exposes an ambiguity, contradiction, or missing safety boundary in the spec/plan/criteria -> treat as"needs-human-review"(or record an authorizedsteerwithkind:"amend_criterion", incrementingcriteria_revision).(2) Actionable defect— proven bug, regression, unmet criterion, or missing verification proof againstARTIFACT+CONTRACT-> route to Step 5 failure triage as"needs-fix"(failure_class: "product", or"harness"when isolated to test/env setup).(3) Explicit Ruling— bounded non-defect tradeoff within the stated load/scope ceiling -> recordRuling: <decision> — <why> — <cost_if_wrong>viasteer(kind:"ruling") and proceed to checkpoint rather than forcing speculative churn.(4) Context noise— false positive disproved by repositoryfile:lineor command exit-code evidence -> dismiss with concretefile:linecitation (verdict: "false-positive"when auditing an external critique; satisfies verification onceCONTRACTproof holds).
Doubt/Review TheaterCircuit Breaker: if>= 2consecutive verification (AdversarialVerify) or final-gate review cycles return prose critiques ("substantive findings") with0actionable defects passing Tier 1–2, halt automated re-spinning immediately—do not invent blocking nits or burnproduct_failures; either checkpoint via an explicit Tier 3Ruling:(withcost_if_wrong) or escalate ("needs-human-review") to the user.
- Checkpoint: when
verdictis"confirmed"(or"false-positive"on a dismissed critique withCONTRACTproof green, or"light"checks pass), runsh <plugin>/hooks/run.sh goal-done <goal-id> --json -- <verification-cmd>to atomically execute the real non-echo verification command, write and validate.omagy/evidence/goal-<id>.json(VERIFICATION_VERDICTS+verified_head), mark the goalstatus:"complete"ingoals.json, and append thecheckpointline (criteria_revisionbound) toledger.jsonl(or updategoals.json+ledger.jsonlmanually when custom multi-verdict metadata is required). Update.omagy/ultragoal/notepad.md(## Priority/## Working/## Manual) when rulings or cross-goal context change. When rendering ledger cells into Markdown or CSV tables, sanitize leading formula characters (=,+,-,@,\t,\r) viarenderLedgerCell. Refreshupdated_atin state. - Failure triage (
productvsharness), unavailable verification & blocked-goal cascade:- Unavailable verification never fabricates completion: if the required test runner, verifier subagent, or external environment is unavailable or indeterminate, never mark the goal
completeand never fabricate passing evidence. Record a truthful non-terminalblockedledger entry (event:"blocked",status:"blocked",note:"verification-unavailable:<reason>") and keep the goalin_progressorblockeduntil verification can actually run. - If verification fails with
failure_class: "harness"(test runner setup, missing fixture, port/env glitch), run up to 1 bounded harness-repair attempt without incrementingproduct_failures. - If verification fails with
failure_class: "product", incrementproduct_failures(max 3 attempts per goal). After 3 product failures or"needs-human-review", set the goalstatus:"blocked"([~]), appendblockedto the ledger, and cascadestatus:"blocked"(note:"blocked-by:<goal_id>") to every downstreampendinggoal whosedepends_ontransitively includes this goal. Continue with remaining independentpendinggoals; if none remain and user input is required, write statecurrent_phase:"blocked",active:false, and ask.
- Unavailable verification never fabricates completion: if the required test runner, verifier subagent, or external environment is unavailable or indeterminate, never mark the goal
Explicit steering & stale-goal reconciliation
- Stale-Goal Reconciliation (on start/resume): Before executing a
pendinggoal, run observable repo checks (fileExists,fileContains,gitGrep) against its target paths. If the repository already satisfies a goal's acceptance criteria from earlier work, verify with targeted tests and record acheckpointwithnote:"reconciled-from-repo"instead of re-implementing. - Explicit Steering: Change the decomposition only with evidence. Append a
steerledger entry withkind,evidence, andrationale, then editgoals.jsonaccordingly. Supported kinds:add_subgoal,split_subgoal,reorder_pending,revise_pending_wording,amend_criterion,annotate_ledger,mark_blocked_superseded. Never silently delete goals. Mark themsupersededinstead. - Criterion Amendment,
criteria_revisionBinding & Autonomous Ruling Audit Trail (Rulings, not stalls): Whenever a goal's acceptance criteria or invariants ingoals.jsonare amended after creation, increment top-levelcriteria_revision(default1) ingoals.jsonand append asteer(kind:"amend_criterion"orkind:"ruling") ledger entry recordingcriteria_revision,decision(orprevious_criterion/amended_criterion),rationale,evidence, andcost_if_wrong("Ruling: <what was decided> — <why> — <cost_if_wrong>"). Anycheckpointorfinal-gatereceipt recorded against an oldercriteria_revisionis stale and must be re-verified against the currentcriteria_revisionbefore closeout. Surface all autonomous rulings and any deferred minor review observations explicitly under"Rulings made & Deferred minors"in the final closeout report. Ordinary prose does not mutate the plan.
Team bridge
For parallel story execution, run $team against the active goals. Team workers return task evidence only. The Ultragoal leader alone updates goals.json and the ledger.
Final gate and exit evidence
Before final completion (phase reviewing):
- Run targeted verification for every goal.
- Run
$ai-slop-cleaneron the changed files, then rerun verification. - Audit every invariant from
goals.jsonand the brief/spec/steering against implementation, tests, and review evidence. - Run
$code-reviewthrough independentcode-reviewerandarchitectsubagent lanes. If review or invariant proof is not clean, add aResolve final code-review blockersgoal with the findings, appendreview-blockers, and loop back to execution. Inside Autopilot, design-level findings return Autopilot toralplan. - When clean: append a
final-gateledger entry with cleaner, verification, review, and invariant evidence. Standalone: write the state terminal (active:false,current_phase:"complete",completed_at). Inside Autopilot: sethandoff_artifacts.ultragoaland let Autopilot finish.
Report goal ids/statuses, ledger path, review verdicts, and any blocker. Never claim completion from state files alone. Completion requires the verification evidence in the ledger.
Resume
On continue/resume, read goals.json, the tail of ledger.jsonl, and the state file, then resume from the first non-complete goal. Do not re-decompose an existing plan unless steering is justified.
- Resumed-run
started-edge closeout bound: when resuming an interrupted or previously blocked goal, append a freshstartedledger entry (event:"started"). Only verification runs andcheckpointentries recorded strictly after that latest unmatchedstartedentry count toward closing out the resumed goal — pre-resume notes or stale artifacts from an earlier attempt never satisfy closeout.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

