spec-and-plan
Skill0 starsChanged 5 months agoMITView on GitHub
Spec-first workflow for any feature or change expected to exceed one atomic commit, and for all work handed between Chef, Jo, or agent sessions. MUST be used when starting a new feature, refactor, or integration (House Elf features, MCP server changes, relay work, x402 extensions) — write the spec BEFORE any code. Also trigger on "plan this", "break this down", "spec this out", or when a task will be executed by a different session/model than the one planning it.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- PanQiWei/pqw-skillstheir own version, first seen Nov 15, 2026
- alphasafal/production-agent-skillstheir own version, first seen Oct 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- alphasafal/production-agent-skills★ 1same name
- PanQiWei/pqw-skills★ 1same 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 repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- doubt-driven-reviewSkill
- gate-backtestSkill
- gate-retrospectiveSkill
- git-disciplineSkill
- solana-security-hardeningSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 46
Check off tasks in the spec file as commits land.
- Distinctive: line 48
When the plan is complete, the spec's Invariants section becomes the claim list for the final doubt-driven review.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Spec and Plan
Code written without a spec optimizes for the first interpretation, not the right one. This skill front-loads the disagreement.
Step 1: Spec (before any code)
Write specs/SPEC-<feature>-<YYYYMMDD>.md:
# SPEC: <feature>
## Problem — what breaks or is missing today, in user/agent terms
## Non-goals — what this explicitly does NOT do (at least 2)
## Interface — exact function signatures, message formats, account layouts, or UI states. No prose where a type will do.
## Invariants — what must remain true after this ships (these become doubt-driven-review claims)
## Open questions — anything unresolved, each assigned to a personRules:
- A spec with zero non-goals or zero open questions has not been thought about hard enough. Add them or state why the task is genuinely trivial — in which case it doesn't need this skill.
- Interfaces are written in the target language (Rust types, JSON schemas), not English descriptions of them.
- The spec is the handoff unit. Jo or an agent session should be able to execute from the spec alone, without this conversation's history.
Step 2: Plan
Append to the same spec file:
## Plan
- [ ] Task 1 — <one atomic commit, ~100 lines max, independently verifiable>
- [ ] Task 2 — ...
## Verification per task — how each task is proven done (test name, manual check, or invariant)Rules:
- Each task must be completable and verifiable in isolation. If a task can't be verified until three tasks later, restructure.
- Tasks touching contract paths inherit the doubt-driven-review + security-hardening gates automatically.
- Order tasks so the system compiles/runs after every commit. No "big bang" integration steps.
Step 3: Execute against the plan
- Check off tasks in the spec file as commits land; the commit message references the spec (
SPEC-<feature>: task N). - Scope drift rule: work not in the plan gets added to the plan first (one line, with verification), then implemented. Undeclared drift is how immutable mistakes ship.
- When the plan is complete, the spec's Invariants section becomes the claim list for the final doubt-driven review.
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.

