Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/phase-gate/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/greenmtnsun/giteasy/phase-gate)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/phase-gate"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/phase-gate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/phase-gate"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/phase-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.00953 |
| Opus 5.5 | $0.00028 | $0.00381 |
| Sonnet 5.5 | $0.00014 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
phase-gate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
software-creation§8 for the phase model.dr-authorfor DR mechanics.
Phase-gate workflow
Phases are the project's heartbeat: each one has explicit entry and exit criteria. A phase transition is the moment to clean up loose ends from the closing phase and verify readiness for the next.
Phase model is project-defined
The phase model — count, numbering, naming, scope of each — is project-defined.
This skill walks the mechanic (reconcile DRs at transition, update
Docs/PHASE.txt, verify next-phase entry criteria) regardless of how phases
are labeled. Triggers fire on "Phase X done" / "ready for Phase Y" without
prescribing what X and Y mean. Project examples observed in the suite:
ModuleWorkshop (Phases 1, 2), DBCCProject (Phase 0 hardening), PesterForge
(Phases 1–3 plus a DR-26 coverage audit outside the numbered ladder),
PhotoOrganizer (Phases 0–3 with 2.0/2.1/3.0/3.1/3.2 sub-phases).
When this skill triggers
Keith says one of:
- "Phase N is done"
- "Ready to move to Phase N+1"
- "Where do we stand on Phase N"
- "Closing out Phase N"
- "Start Phase N+1"
What this skill does at trigger
1. Reconcile every DR for the closing phase
For each DR in Docs/DECISIONS_PHASE<N>.md:
- If the code matches the decision → flip status to
DECIDED (YYYY-MM-DD)with today's date - If the code drifts from the decision → keep status, add a Drift Notice (see software-creation §7) with file:line and a recommended fix path
- If the DR is partially implemented → keep status
OPEN · note, add an Implementation Note with what works, what doesn't, what would close the gap - If the DR is no longer relevant → mark
SUPERSEDEDand link the replacing DR (or note "scope dropped")
2. Update Docs/PHASE.txt
Single line, current phase number only:
2
This file is the source of truth for which phase is active. (Correction 2026-08-15: the global CLAUDE.md does NOT reference PHASE.txt — §13 references Docs/PIPELINE.md; only per-project docs may cite PHASE.txt.) Future automation reads it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 81 lines · 70 tokens per session scan A d7ad6d87de68
phase-gate is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 70 tokens to every session and 953 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-18.
phase-gate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| phase-gategreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 70 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |