godmode-continuity
Reconstruct and preserve private project continuity from local evidence.
Skill by AIimagined
Chalk Labs
Need help deploying godmode-continuity?
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-continuity
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
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-continuity
What's inside
- Skill name
godmode-continuity- Description
- Reconstruct and preserve private project continuity from local evidence. Use when resuming work, changing branches or worktrees, detecting drift, recording handoffs, or explaining why context is missing or stale. Not for code investigation or release steps.
- License
- Apache-2.0
- Instructions
- 71 lines in SKILL.md · view on GitHub
Files (5)
- PURPOSE.md
- SKILL.md
- openai.yaml · agents/
- godmode-evals.json
- godmode-continuity-schema.md · references/
SKILL.md (first lines)
# Godmode Continuity ## Outcome Produce a bounded context brief whose claims can be traced to current inspection or a validated local record, then preserve the next recovery point outside the working tree. ## Reconstruct current reality 1. Resolve project, Git-common-directory, worktree, branch, HEAD, and hashed-remote identity before trusting prior state. 2. Run `context status`; add `--scan` when filesystem drift matters. 3. Run `inventory diff` to distinguish added, changed, and removed paths from the last baseline. Do not infer file content from hashes. 4. Run `resume` after a valid baseline or `resume --refresh` when evidence is stale. 5. Classify each brief item as observed fact, declared intent, assumption, conflict, invariant, decision, incident, open check, or obligation. Treat identity drift, contradictory invariants, phantom file references, undocumented changes, unproven completion, and capacity overflow as findings—not as facts to hide. ## Preserve continuity Use the narrow record type: - `remember --kind decision|invariant|lesson|obligation` for durable knowledge. - `remember --kind lesson --enforce 'kind=<kind>;predicate=<field op value>'` (needs `--guard`). - Enforce makes a guard executable: a matching write of that kind is refused, guard as remedy. - Forbids `refusal`/`action`/`checkpoint` kinds as enforce targets; literals cap at 256 characters. - `matches` allows at most one quantifier on an atom or class, never a group, at parse time. - A `matches` field over 4096 characters refuses the write outright - never truncated or silent. - A later lesson must reaffirm `--enforce` or set status `superseded`, `retired`, or `candidate`. - `checklist update` for cumulative checks. - `checkpoint` for a recoverable state, next actions, active hypothesis, and evidence; `--owes "<restore>"` for a temporary change left behind (a role bump, a throwaway spec) that the scope gate names until it is closed. - `branches --record`, `version`, `db`, `sprint`, or `docs` for domain state. Record relative paths, statuses, hashes, and evidence references. Never record raw prompts, conversations, tool transcripts, source bodies, secrets, or environment dumps. A lesson may describe a failure and generalized guard, but should not preserve sensitive failure payloads. ## Completion gate Before ending or compacting a session, record what changed, what was verified, what is still uncertain, and the next executable action. A `complete`, `fixed`, or `done` status requires fresh evidence. Run `doctor` after a material continuity change. Godmode cannot guarantee perfect memory. If no valid baseline or adapter exists, say so and give the exact rebuild action. Status truth lives in one writable store: `status set|survey|remaining|render|handover` (pending items are existence-checked; phantoms close with evidence). `context why --about X` answers with the recorded decisions, fixes, dependencies, and invariants touching a surface; `slice` reads bounded file ranges that declare their own truncation; `absorb --path X` proves a synced file is truly absorbed. Read [godmode-continuity-schema.md](references/godmode-continuity-schema.md) when choosing record types or interpreting detector output. ## Verbs at the moment of demand - Opening and closing: `godmode session open` states identity, dirty files, plan, obligations and the host's enforcement table; `godmode session close` refuses an unattested rule or an uncited claim; `godmode brief` prints the continuity brief on demand. - Memory hygiene: `godmode hygiene` lists near-duplicate and contradicting lessons and decisions among the newest active records per kind; supersede the loser with `remember --status superseded`. - Forgetting: `godmode forget` expires old episodes into a cold, still-chained segment (action and refusal after 30 days, attestation after 90), reports supersession chains and flags contradictions as `review` records that `status` and `hygiene` surface until they are acknowledged or dismissed (`remember --kind review --review seq:<n>` names which one a closure closes). A record cited by a live claim, a checkpoint, a law guard or a pin never expires; `--now` previews another clock and is accepted with `--dry-run` only; `history --seq` still reaches a cold record, re-hashing it before it serves it. - What happened: `godmode history` walks the record, `godmode actions` lists tool actions the gate saw, `godmode inventory` snapshots the tree, `godmode drift` names what moved since, `godmode report` and `godmode export` render the record for a reader or another tool, `godmode index` rebuilds the lookup index. - When the anchor is wrong: `godmode reanchor` re-binds the archive to the repository, `godmode rewind` returns to a recorded state, `godmode replay` re-reads a recorded run. - Work in flight: `godmode planmode check` holds an edit to the approved plan, `godmode build` records a build outcome, `godmode fleet` lists the sessions on this machine, `godmode examples` and `godmode guide` show the recorded rules in use, `godmode selftest` proves the install itself, and `godmode claim --stale` names claims whose cited evidence moved.
From AIimagined/Godmode, Apache-2.0.
More from AIimagined/Godmode
- 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-second-look
AIimagined
Independently recheck a change, session, PR, or diff that already carries an accepted claim or verdict.
SkillAFreshness: A★ 6Claude Code +9 - 0.622score
godmode-skill-eval
AIimagined
Score a drafted or hand-edited skill's authored routing rows against the committed baseline, and confirm its bundle validates, before it ships or is enabled…
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
Signals
- Stars
- 6
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 28, 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 - 0.624score
godmode-governance
AIimagined
Preview and govern protected engineering actions without executing them implicitly.
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-skill-eval
AIimagined
Score a drafted or hand-edited skill's authored routing rows against the committed baseline, and confirm its bundle validates, before it ships or is enabled…
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-continuity 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-continuity skill. Agent Mart. https://agentmart.dev/skills/aiimagined-godmode-continuity (last updated 2026-10-24)