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 gsaranti/pantheon --skill metis-review-taskgit clone --depth 1 https://github.com/gsaranti/pantheonWrote 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/gsaranti/pantheon/metis-review-task)<a href="https://agentmods.dev/skills/gsaranti/pantheon/metis-review-task"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-review-task/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/gsaranti/pantheon/metis-review-task"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-review-task.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 | $0.00034 | $0.00727 |
| Opus 5 | $0.00017 | $0.00364 |
| Sonnet 5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
metis-review-task 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/metis-review-task
Dispatch the metis-task-reviewer subagent to review one implementation against the description and plan it was meant to satisfy.
Arguments
- Trailing prompt — optional. Augments the dispatch prompt per the command-prompts convention (e.g., narrowing the diff range, flagging a specific concern).
Context expected
The parent collects what the reviewer needs from conversation context before dispatching:
- The description the work was implemented against — from this session's chat history, or rehydrated from
.metis/CURRENT.mdvia/metis-session-start. - The plan, if one was produced — same sources.
- The implementer's scope report — produced by
/metis-implement-taskat the close of implementation; in chat history or in.metis/CURRENT.md.
If any of these are missing, ask the user before dispatching. Reviewing an unstated brief is the silent-drift mirror of implementing one.
Preflight
Run references/review-task-preflight.sh. It exits non-zero if the working directory isn't a git repo. On success it reports two fields:
BASELINE— the branch the implementation diverges from. First existing ofmain,master,origin/main,origin/master; empty if none exist (the subagent then reviews only uncommitted changes).DIFF_PRESENT—yesif there are uncommitted changes or commits ahead ofBASELINE;nootherwise.
If DIFF_PRESENT=no, surface an "empty diff" finding without dispatching — no implementation work to judge.
Subagent dispatch
Dispatch the metis-task-reviewer subagent with a single structured prompt containing:
- The description.
- The plan, if one was produced.
- The implementer's scope report.
- The
BASELINEfrom the preflight (the branch the subagent should diff against). - Any trailing prompt the user passed to this skill, verbatim.
The subagent reads the git diff itself; the parent does not need to embed it.
Write scope
This command writes nothing.
Invocation prompt
What ships with it
1 file 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.
- 10d ago First seen · 68 lines · 34 tokens per session scan A 417a1d4ca704
metis-review-task is a skill published in the GitHub repository gsaranti/pantheon (3 stars, last pushed 18d ago), licensed MIT. It adds 34 tokens to every session and 727 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
developer-anti-patterns-to-avoid
ANTI-PATTERNS TO AVOID — extracted from roles.json deepPrompt for developer.
developer-git-workflow
GIT WORKFLOW — extracted from roles.json deepPrompt for developer.
security-review
Use this skill to review code changes for security concerns before they merge. Covers input validation, authentication and authorization, secrets handling, injection surfaces (SQL, command, template, prompt), unsafe APIs and dependencies, sensitive data handling, and output encoding. Runs against the current diff (NOT…
serena-refactor
This skill should be used when the user asks to "rename function", "refactor code", "rename symbol across codebase", "change function signature", "restructure code safely", or mentions Serena's renamesymbol or replacesymbolbody tools.
review-changes
Review uncommitted code changes for bugs, security vulnerabilities, and quality issues. Use before commits or when asked to review code.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.