forge-verify
Skill2 starsChanged 4 months agoMITView on GitHub
Run forgekit's turn-commit-PR verification-gate lattice before you commit or push. Use when starting a task (preflight), staging a commit (precommit), or opening a PR (verify) — never push without verify + precommit green.
- Installs packages
- Commits and pushes
3 other projects use a version of this.
Adopted by
Most recently taken up by
- brightstack/forgetheir own version, first seen Nov 8, 2026
- ForgeyClap/claude-forgetheir own version, first seen Oct 11, 2026
- ForgeyClap/Forge-Coretheir own version, first seen Oct 11, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- brightstack/forge★ 13same name
- ForgeyClap/claude-forge★ 2same name
- ForgeyClap/Forge-Core★ 2same 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.
- CLAUDE.mdCLAUDE.md
- global/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- forge-impactSkill
- forge-ledgerSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 55
If a gate fails intermittently, re-run it once before investigating (flakes happen).
“Common” is measured: kept by at least 6 in 10 of the 3 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-verify — the pre-push verification gate
Install
# from a forgekit checkout, or: npm install -g forgekit
# then copy the skill into your project (or ~/.claude/skills for global use):
cp -r skills/forge-verify .claude/skills/Requires the forge CLI on PATH (npm install -g forgekit, or node <checkout>/src/cli.js).
When to use
- Starting any coding task → run
forge preflightfirst. - About to
git commit→ runforge precommitfirst. - About to
git pushor open a PR → runforge verifyfirst. - CI failed and you want the same checks locally before pushing again.
The lattice
task start commit push / PR
│ │ │
▼ ▼ ▼
forge preflight → forge precommit ──green──→ forge verify ──green──→ pushEach gate is independent and evidence-producing: it prints what it checked and what failed, so a red gate tells you exactly what to fix. See references/gate-lattice.md for the full turn ⊂ commit ⊂ PR model.
Commands
forge preflight # assumption check: what the task names that the repo doesn't define
forge precommit # commit-level gate: staged code w/o docs + secret scan
forge verify # independent verification: tests + hallucinated-symbol + provenance
forge verify --deep # multi-lens consensus (slower, for risky changes)FORGE_COMMIT_GATE=block|warn|0 tunes how hard precommit fails (default: warn).
Rules
- Never push without
forge verify+forge precommitpassing. That is the whole point. - A red gate is a finding, not a suggestion — fix the code, don't argue with the gate.
- If a gate fails intermittently, re-run it once before investigating (flakes happen); if it fails twice, it's real.
--deepis for risky changes (security, migrations, public API). Routine edits use the default gate.
References
- references/gate-lattice.md — the turn ⊂ commit ⊂ PR model
- references/what-verify-checks.md — what each gate actually runs
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.

