forge-build
Skill0 starsChanged 19 days agoMITView on GitHub
Use when the user supplies an approved or frozen work order for one executor, including a bounded refactor, migration, bug fix with a known repro, or test-writing task. Use forge-orchestrate for multiple parallel units and forge for unresolved design. Do not use for tiny edits, code review, or work that requires Claude-session-only tools.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- brightstack/forgetheir own version, first seen Nov 8, 2026
- KhaledAufDB/lakeforgetheir own version, first seen Oct 13, 2026
- tinyorbit-ai/skillstheir own version, first seen Aug 20, 2026
- redteamlife/forgetheir own version, first seen Jul 26, 2026
- tonmoy007/forge-pluginstheir own version, first seen Jun 9, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- brightstack/forge★ 13same name
- tonmoy007/forge-plugins★ 2same name
- redteamlife/forge★ 1same name
- tinyorbit-ai/skills★ 1same name
- KhaledAufDB/lakeforge★ 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 repository5 other files it gives its agents.
- forge-orchestrateSkill
- forge-recoverySkill
- forge-reviewSkill
- forgeSkill
- forge-with-docsSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Route first: Read ../forge/SKILL.md, resolve the active profile, and use ../forge/ENGINE.md for preflight before any launch.
- Very specific: line 37
Before product execution, read ../forge/SKILL.md and the one selected file in ../forge/profiles/.
- Very specific: line 51
Don't review already-written code — that's /codex:review.
- Distinctive: line 52
Don't restate Act-3/4 cadence here.
- Very specific: line 53
Don't run assured ceremony under sprint, or wait for a Gate-2/Gate-3 that does not exist.
- Distinctive: line 54
Don't let the executor commit or merge.
“Common” is measured: kept by at least 6 in 10 of the 5 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
FORGE-BUILD — Hand a Frozen Spec to One Model
Act 3 standalone: a locked spec goes to a single executor; the Claude-side driver
owns the outcome. Use it when the work reads as a work order for ONE model. For a
multi-unit split use /forge-orchestrate; to plan first use /forge.
Unique to this skill
- Route first. Read
../forge/SKILL.md, resolve the active profile, and use../forge/ENGINE.mdfor preflight before any launch. The steps below do not override that profile. - Preconditions.
SPEC_FILEmust read as a work order.git status -sb— a launch needs a clean tree (a guarded expansion of an already-writing lane may carry its expected dirty tree). - Build contract → temp file (never inline-quote): GOAL · SPEC (implement exactly;
report deviations, not redesigns) · KEY PATHS · CONSTRAINTS · NON-GOALS · PROOF
(the exact command, and whether it is
targetedorbroad) · OUTPUT (files-changed report + proof output + deviations). - Launch per
../forge/references/invocation-templates.md§4c, captureTHREAD_ID. Work over ~10 min runs backgrounded with a loud completion banner; check liveness by the clock, never a self-report (../forge/references/liveness.md). - Fix loop. Problems resume the SAME session (§4d) with a fix-list temp file, up to
MAX_FIX_ROUNDS(default 2), then the driver takes over and logs it. - Log. Append the round and its verdict to
LOG_FILE.
Tunables: SPEC_FILE=PLAN.md · MAX_FIX_ROUNDS=2 · LOG_FILE=PLAN-REVIEW-LOG.md ·
PROOF_CMD (from the spec; if absent, ask one question).
Execution profile
Before product execution, read ../forge/SKILL.md and the one
selected file in ../forge/profiles/. Those sources alone own
cadence, review, proof, routing, and integration. Do not reconstruct or add ceremony
here. Every lane still passes ../forge/dispatch-guard.sh.
Canonical references
../forge/ROUTING-POLICY.md (routing) ·
../forge/profiles/ (cadence) ·
../forge/ENGINE.md (engine, templates, admission) ·
../forge/references/ (detail, on demand)
What NOT to do
- Don't review already-written code — that's
/codex:review. - Don't restate Act-3/4 cadence here; the profile owns it.
- Don't run
assuredceremony undersprint, or wait for a Gate-2/Gate-3 that does not exist. - Don't let the executor commit or merge.
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.

