godmode-research
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…
Skill by AIimagined
Chalk Labs
Need help deploying godmode-research?
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-research
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: research
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-research
What's inside
- Skill name
godmode-research- Description
- 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 import verdict and a behaviour verdict, refusing adopt or extend on a surface-only reading. Use when an outside codebase is being surveyed for a mechanism worth borrowing. Not for rebuilding that mechanism under Godmode names, and not for root-causing a failure in this repository.
- License
- Apache-2.0
- Instructions
- 52 lines in SKILL.md · view on GitHub
Files (4)
- PURPOSE.md
- SKILL.md
- openai.yaml · agents/
- godmode-evals.json
SKILL.md (first lines)
# Godmode Research ## Outcome An outside source is judged on what was actually opened, not on its landing page: every file read carries a receipt with its line range and a digest of the slice, the licence is classified before anything else, and the recorded verdict pair (import and behaviour) is refused as adopt or extend unless a receipt names a source file rather than a README, a doc or a release note. ## Use - An outside repository is being surveyed for a mechanism this project might borrow. - An earlier survey recorded a verdict and its reading depth is in doubt. - A source's licence has to be classified before any of it is studied closely. - A survey needs to show, per source, how many files were opened and whether it stayed on the surface. ## Do Not Use - Rebuilding a studied mechanism in stdlib under Godmode names and pinning it with a reproducing test - that is `godmode-replicate`. - Root-causing a failure inside this repository - that is `godmode-investigation`. - Independently rechecking a verdict another pass already accepted - that is `godmode-second-look`. ## Deterministic Execution Flow 1. **Licence first.** `godmode license check --operation "<the survey, naming the source>"` - whether an operation naming that source may proceed at all. Then read the licence file with a receipt: `godmode read --source <name> --path LICENSE --root <local checkout of the source>`, and classify it: `godmode license attest --repo <name> --classification <permissive|proprietary-no-redistribution|unlicensed|copyleft-incompatible> --clean-room-note "<what was read versus written>"` (the note is required for anything but permissive). - Fallback: a refusal from `license check`, or a classification other than permissive, ends the survey at `import_verdict: skip` - record that and stop. 2. **Tree, then the implementing files.** List the source's tree and name the two or three files that implement the claimed mechanism. `godmode upstream --path <local checkout> --skills <keyword>` lists the skill and doc files that mention the mechanism, with line numbers, and records nothing - a pointer to where the code lives, never a substitute for reading it. 3. **Receipt every implementing file.** `godmode read --source <name> --path <implementing file> --root <local checkout> --lines <a-b>` - one receipt per file opened: path, line range, and a digest of the slice. 4. **Measure the reading depth.** `godmode parity --sources` - per source, `files_opened` and `surface_only`. A source still `surface_only: true` has not been read; go back to step 3. 5. **Record both verdicts.** `godmode remember --kind decision --subject "absorb:<name> <date>" --value "<finding> import_verdict: <adopt|extend|diverge|skip|exists|unread|n-a> behaviour_verdict: <confirmed-have|confirmed-dont|unverified>" --evidence receipt:<name>:<implementing file>` - refused `surface-only` when adopt or extend cites only README, docs or release-note receipts, and refused naming either missing verdict. 6. **Dispose each symbol with no counterpart when comparing a copied tree.** `godmode upstream --path <local checkout> --dispose <SYMBOL>=<adopt|extend|diverge-deliberately|n-slash-a-different-surface>:<confirmed-we-have-it|confirmed-we-dont|unverified> --evidence receipt:<name>:<file>`. Read [PURPOSE.md](PURPOSE.md) for the archive records this skill exists to close. ## Must Not - Never record adopt or extend from a README, doc or release-note reading; the verdict for a surface read is unread, skip or diverge. - Never study a source's code before its licence is classified in step 1; instead classify the licence first and stop if it forbids the use. - Never name the studied source in shipped text (code, docs, skills, changelog); instead describe the mechanism in Godmode's own words and keep the name in the private record. - Never copy source text into this repository; a mechanism is carried over only by `godmode-replicate`, rewritten under Godmode names. - Never skip the receipt for a file that the verdict relies on; an unreceipted read is invisible to `parity --sources`. ## Acceptance - `godmode parity --sources` reports `surface_only: false` for every source whose verdict is adopt or extend. - Every `absorb:` decision carries both verdicts and at least one receipt naming a source file. 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-impact-gate
AIimagined
Score a staged commit's fan-out and architectural-boundary crossings just before committing: dependents left unfollowed, hook-to-runtime import direction…
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-research 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-research skill. Agent Mart. https://agentmart.dev/skills/aiimagined-godmode-research (last updated 2026-10-24)