anti-phase-skip
phase lifecycle, runtime validation, integration closure
Skill by datacosmos-br
Chalk Labs
Need help deploying anti-phase-skip?
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/datacosmos-br-anti-phase-skip
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: agent-building
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 Nov 2, 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/anti-phase-skip
What's inside
- Skill name
anti-phase-skip- Description
- phase lifecycle, runtime validation, integration closure
- License
- MIT
- Metadata
- version: 1.0.0 · aihub.tags: ["decision:ADR-0008","effective:2026-08-29","usage:router"]
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- openai.yaml · agents/
- procedure.md · references/
SKILL.md (first lines)
# Anti Phase Skip Skipping a phase cycle is a critical delivery defect. It creates false DONE claims, unmerged behavior, stale validation, open tracker state, abandoned WIP, and runtime failures that green unit tests cannot expose. Activate before changing tasks, advancing a plan phase, handing off, or claiming completion. Read the `complete procedure` (skill file). A phase is DONE only when `rules/law.md` item 10 holds with fresh evidence: real runtime, native gates, a reviewed and merged PR, post-merge runtime, zero residue and tracker closure. A missing step keeps the phase open, nothing starts beside it, and incomplete work is pushed only to a preservation ref. An external-token validation excluded before invocation is recorded as `NOT EXECUTED`, not green, and does not become a missing phase step. If invoked, it is applicable and any credential or runtime failure remains red. Only an explicit operator decision may pause, reorder, or replace a phase. A failed check, actionable review, open PR, pending approval, or merge conflict is work inside the phase: fix, publish, revalidate, and continue through landing. Report and request help only after every authorized correction is exhausted and the remaining condition is external or requires new authority. During tracker suspension, create no substitute tracker or ledger, preserve evidence only in separately authorized Git/PR/CI, and keep closure unavailable.
From datacosmos-br/agents, MIT.
More from datacosmos-br/agents
- 0.560score
artifacts
datacosmos-br
html artifact, sidebar, client-side routing, inventory
SkillAFreshness: AClaude Code +9 - 0.558score
fix-forward
datacosmos-br
concurrent work, integration adoption, anti-rollback coordination
SkillAFreshness: AClaude Code +9 - 0.558score
agents-refactor
datacosmos-br
agent instruction refactoring, progressive disclosure, contradiction resolution
SkillAFreshness: AClaude Code +9 - 0.558score
sprint-closure
datacosmos-br
increment closure, integration evidence, residue elimination
SkillAFreshness: AClaude Code +9 - 0.558score
conformance-sweep-loop
datacosmos-br
conformance sweep loop, class-wave repair map, git-dep bump, declaration-first scoping
SkillAFreshness: AClaude Code +9 - 0.558score
execution-law
datacosmos-br
sole-executor engagement, startup census, coordinator ladder, adoption, extermination, landing
SkillAFreshness: AClaude Code +9 - 0.558score
release-closeout
datacosmos-br
integration closeout, push-sync audit, superproject merge, lane commits, tracker evidence
SkillAFreshness: AClaude Code +9 - 0.558score
safe-delete
datacosmos-br
safe deletion, atomic obsolete-code extermination, artifact retirement, recovery evidence
SkillAFreshness: AClaude Code +9 - 0.555score
skill-governance
datacosmos-br
skill authoring, bundle governance, semantic evaluation
SkillAFreshness: AClaude Code +9 - 0.555score
dispatch-agent
datacosmos-br
agent delegation, specialist selection, bounded work
SkillAFreshness: AClaude Code +9 - 0.553score
op-learning
datacosmos-br
operator corrections, durable governance, authority reconciliation
SkillAFreshness: AClaude Code +9 - 0.550score
caveman
datacosmos-br
operator communication, concise reporting, evidence first
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 18, 2026 (1 month ago)
- Last release
- Oct 9, 2026 (27 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- MIT
- Repository
- github.com/datacosmos-br/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from datacosmos-br
- 0.560score
artifacts
datacosmos-br
html artifact, sidebar, client-side routing, inventory
SkillAFreshness: AClaude Code +9 - 0.558score
conformance-sweep-loop
datacosmos-br
conformance sweep loop, class-wave repair map, git-dep bump, declaration-first scoping
SkillAFreshness: AClaude Code +9 - 0.558score
safe-delete
datacosmos-br
safe deletion, atomic obsolete-code extermination, artifact retirement, recovery evidence
SkillAFreshness: AClaude Code +9 - 0.558score
agents-refactor
datacosmos-br
agent instruction refactoring, progressive disclosure, contradiction resolution
SkillAFreshness: AClaude Code +9 - 0.558score
sprint-closure
datacosmos-br
increment closure, integration evidence, residue elimination
SkillAFreshness: AClaude Code +9 - 0.558score
execution-law
datacosmos-br
sole-executor engagement, startup census, coordinator ladder, adoption, extermination, landing
SkillAFreshness: AClaude 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 anti-phase-skip 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
anti-phase-skip skill. Agent Mart. https://agentmart.dev/skills/datacosmos-br-anti-phase-skip (last updated 2026-10-24)