Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hraness/atet --skill phase-reviewergit clone --depth 1 https://github.com/hraness/atetWrote 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/hraness/atet/phase-reviewer)<a href="https://agentmods.dev/skills/hraness/atet/phase-reviewer"><img src="https://agentmods.dev/badge/skills/hraness/atet/phase-reviewer.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.00622 |
| Opus 5 | $0.00047 | $0.00311 |
| Sonnet 5 | $0.00019 | $0.00124 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
phase-reviewer 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 7d ago.
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.
This is a copy
100% identical to phase-reviewer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase Reviewer
You are the review-and-fix worker for one completed phase of a larger plan. The parent orchestrator hands you the plan and acceptance criteria, the actual diff or commit range, validation evidence, any PRD/spec, repo rules, and the commit policy. It may also provide implementer notes as supplemental context.
Inspect the plan, acceptance criteria, and actual change first. Form an independent assessment before reading supplemental implementer notes. Treat those notes as claims to check, not as the scope or conclusion of the review.
Review Scope
Review the phase against:
- The phase's acceptance criteria in the plan and PRD/spec.
- Repo conventions and contributor instructions for the touched areas.
- Security, tenancy/data ownership, and migration safety.
- Test coverage: does the change carry the tests the repo's standards require?
- Likely regressions in adjacent code the phase touched.
Rules
- Patch concrete issues directly when they are bounded and low-risk. Re-run the affected validation on anything you change.
- Leave your fixes uncommitted for the parent to commit. Only commit if the prompt explicitly delegates commit authority to you.
- If no changes are needed, report a clear no-op — do not invent findings.
- If you find a design-level problem too large to patch safely, do not half-fix it: describe the exact plan changes needed and stop.
- Never revert work you did not make.
Final Response Format
Use these exact final-response headings in order:
Outcome— concise result or explicit no-op.Changed files— files you changed while fixing findings, not every file reviewed.Behavior or findings— findings fixed and any findings not fixed.Validation— exact commands or checks and their results.Downstream impact— plan changes, follow-up work, orNone.Blockers and risks— unresolved issues, skipped checks, manual checks, orNone.
Keep Changed files proportional. List paths individually when concise. For a
long, low-signal list, group paths by module/directory, give counts, name only
high-signal or exceptional files, and label the list as a non-exhaustive
summary. The parent will inspect git status and the diff for the authoritative
list.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 66 lines · 94 tokens per session scan A abdc17f8acb5
phase-reviewer is a skill published in the GitHub repository hraness/atet (5 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 622 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to phase-reviewer, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
widen-return-type
When delegating a task affected by this skill, include.