godmode-impact-gate
Score a staged commit's fan-out and architectural-boundary crossings just before committing: dependents left unfollowed, hook-to-runtime import direction…
Skill by AIimagined
Chalk Labs
Need help deploying godmode-impact-gate?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/aiimagined-godmode-impact-gate
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/godmode-impact-gate
What's inside
- Skill name
godmode-impact-gate- Description
- Score a staged commit's fan-out and architectural-boundary crossings just before committing: dependents left unfollowed, hook-to-runtime import direction, paths outside the plan's editable fence, paired artifacts left behind, and the green retests the commit-time closure refusal will demand, with a recorded decision as the named escape hatch. Use before committing a multi-module edit. Not for answering who-calls questions ahead of an edit, and not for authorizing a push or release.
- License
- Apache-2.0
- Instructions
- 57 lines in SKILL.md · view on GitHub
Files (4)
- PURPOSE.md
- SKILL.md
- openai.yaml · agents/
- godmode-evals.json
SKILL.md (first lines)
# Godmode Impact Gate ## Outcome Before `git commit`, the staged edit's reach is scored against the project's own graph and boundaries - how many dependents it leaves unfollowed, whether it crosses the hooks/runtime import boundary, whether it steps outside the declared fence or leaves a paired artifact behind - and every finding is either fixed or accepted on the record through one named escape hatch. The gate is advisory; the one refusal that is not (the commit-time closure check) is satisfied by running the retests, never waived. ## Use - A multi-module edit is staged and about to be committed. - A commit touches `hooks/` or `scripts/godmode_runtime/` and the import direction between them must hold. - A plan declared an editable fence and the staged set may have stepped outside it. - A crossing is intentional and should be accepted on the record rather than silently. ## Do Not Use - Finding who calls or imports a module before planning an edit to it - that is `godmode-codegraph`. - Previewing or authorizing a force push, tag, or release - that is `godmode-governance`. - Diagnosing why a retest went red after an edit - that is `godmode-investigation`. ## Deterministic Execution Flow 1. **Open a session, then enumerate the staged work and its size pressure.** `godmode session open` (if none is open; steps 6 and 7 refuse without one), then `godmode scope --minimality` - lists what changed against the working tree and reports size pressure; it never blocks. - Fallback: outside a git repository it reports `verdict: unavailable`; name the paths explicitly in every later `--changed` instead. 2. **Prove the saved graph before trusting its fan-out.** `godmode atlas graph verify` - reports `verified: false` with a reason when no snapshot exists or it is stale. - Fallback: only then run `godmode atlas graph rebuild`, and repeat step 2. 3. **Score the fan-out.** `godmode atlas closure --changed <path> [<path> ...] --depth 2` - every dependent of a changed path that was not itself changed. `verdict: unfollowed-dependents` (exit 1) is the finding, not an error; the count of dependents is the fan-out score. 4. **Check the architectural boundary.** `godmode atlas --direction` - hooks import the runtime only through the declared surface, and the runtime never imports hooks; exit 1 names each crossing. 5. **Check the declared fence.** `godmode fence audit --changed <path> [<path> ...]` - changed paths outside the plan's editable set. 6. **Check paired artifacts.** `godmode precheck --about "commit <one-line summary>" --changed <path> [<path> ...]` - read `paired_artifacts.verdict`: an artifact declared to change together with a staged path that did not. 7. **Satisfy the commit-time closure refusal.** `godmode retest --run` - runs the tests that pin the changed paths and attests their exit code. The pre-commit closure check refuses a staged code path with no green retest newer than its last edit; it has no escape and none is sought here. 8. **Accept an intended crossing through the named escape hatch.** A fan-out, fence or boundary finding that is deliberate is recorded before the commit: `godmode remember --kind decision --subject "impact-accepted:<path>" --value "<why the crossing is intended and what bounds it>" --evidence seq:<the closure or audit record>`. Size growth past a recorded ceiling is accepted with `godmode minimality --accept-growth <section> --reason "<what the added surface bought>"`. Read [PURPOSE.md](PURPOSE.md) for the archive records this skill exists to close. ## Must Not - Never trust a fan-out from an unverified graph; step 2 comes before step 3, and `rebuild` runs only after `verify` says so. - Never commit with `--no-verify` to get past the closure refusal; run `godmode retest --run` instead. - Never accept a crossing silently; the escape hatch is a recorded decision that names the path and the reason, or it is not accepted. - Never edit the fence or the paired-artifact declarations to make a finding disappear; accept it through the escape hatch or fix the edit. - Never turn this advisory gate into a blocker for a docs-only or fixture-only commit; the closure check exempts those, and so does this skill. ## Acceptance - `godmode atlas closure` names every unfollowed dependent of the staged paths from a verified graph. - Every boundary, fence or fan-out finding is either fixed or carries an `impact-accepted:` decision before the commit. If an assertion cannot be proved, report the unmet assertion and the next safe action rather than the outcome it was meant to prove.
From AIimagined/Godmode, Apache-2.0.
More from AIimagined/Godmode
- 0.627score
godmode-continuity
AIimagined
Reconstruct and preserve private project continuity from local evidence.
SkillAFreshness: A★ 6Claude Code +9 - 0.627score
godmode-investigation
AIimagined
Diagnose technical failures with reproducible evidence and bounded hypotheses.
SkillAFreshness: A★ 6Claude Code +9 - 0.627score
godmode-skill-forge
AIimagined
Create an original, compact project skill after a repeated capability gap is proven.
SkillAFreshness: A★ 6Claude Code +9 - 0.624score
godmode-governance
AIimagined
Preview and govern protected engineering actions without executing them implicitly.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-changelog
AIimagined
Draft and verify release-notes from local commits and changelog fragments.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-ci
AIimagined
Run CI's checks locally, in CI's order, before opening a pull request: the task precheck, the fragment gate against the base branch, the preflight of HEAD or…
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-codegraph
AIimagined
Query a local, on-demand code dependency graph to answer who calls, who imports, and what blast radius a change carries, before spending an unnecessary full…
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-evidence
AIimagined
Shape a claim so its citations grade the first time: reflect it against the record, cite exit-bearing commands through `--verify`, give a hypothesis its…
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-host-sync
AIimagined
Detect every installed AI CLI host, reconcile Godmode's interception manifests into each one's native format, and drift-repair the installed configuration…
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-spec-lifecycle
AIimagined
Move a specification and its plan through specify, approve, implement, review, and status as one linked, resumable record instead of separate hand-authored…
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-research
AIimagined
Study an outside source repository in a fixed order - licence, tree, the two or three implementing source files, line-cited receipts - and record both an…
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-second-look
AIimagined
Independently recheck a change, session, PR, or diff that already carries an accepted claim or verdict.
SkillAFreshness: A★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 25, 2026 (1 month ago)
- Last release
- Oct 5, 2026 (28 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/AIimagined/Godmode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AIimagined
- 0.627score
godmode-skill-forge
AIimagined
Create an original, compact project skill after a repeated capability gap is proven.
SkillAFreshness: A★ 6Claude Code +9 - 0.627score
godmode-investigation
AIimagined
Diagnose technical failures with reproducible evidence and bounded hypotheses.
SkillAFreshness: A★ 6Claude Code +9 - 0.627score
godmode-continuity
AIimagined
Reconstruct and preserve private project continuity from local evidence.
SkillAFreshness: A★ 6Claude Code +9 - 0.624score
godmode-governance
AIimagined
Preview and govern protected engineering actions without executing them implicitly.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-changelog
AIimagined
Draft and verify release-notes from local commits and changelog fragments.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-second-look
AIimagined
Independently recheck a change, session, PR, or diff that already carries an accepted claim or verdict.
SkillAFreshness: A★ 6Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get godmode-impact-gate running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
godmode-impact-gate skill. Agent Mart. https://agentmart.dev/skills/aiimagined-godmode-impact-gate (last updated 2026-10-24)