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 patforna/auto-task --skill review-taskgit clone --depth 1 https://github.com/patforna/auto-taskWrote 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/patforna/auto-task/review-task)<a href="https://agentmods.dev/skills/patforna/auto-task/review-task"><img src="https://agentmods.dev/badge/skills/patforna/auto-task/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/patforna/auto-task/review-task"><img src="https://agentmods.dev/badge/skills/patforna/auto-task/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 | $0.00043 | $0.00563 |
| Opus 5.5 | $0.00017 | $0.00225 |
| Sonnet 5.5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Task
Usage
/at:review-task <task-path> [further user instructions]
Goal
Verify that a task has been completed according to its intent and criteria.
Context
This skill is typically run as part of a larger workflow:
create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task
As steps (e.g. clarify, plan, impl, review) typically run in new sessions, it's imperative that the task file plus repo state carry everything the next agent needs.
Task files live in the project's task store. Project config can override its location and other defaults: read .claude/auto-task.config.md (project, committed) and .claude/auto-task.config.local.md (personal overrides — win on conflict) if they exist. /at:config owns the defaults and the precedence rules.
Guidance (DO NOT IGNORE!)
These rules govern how to perform the review. Internalise and follow them throughout.
- Flag issues — do not attempt to fix them; let the user decide.
Step 1: Build Context
Read the task and the code that was implemented. Ensure you fully understand the task's intent, criteria and what was implemented.
Step 2: Verify ACs
For each acceptance criterion, determine: pass, fail, or unclear.
A criterion passes when you can point to specific evidence — for example, a test that exercises it, observable behaviour in the code, or output from running it. "The code looks like it would work" is not evidence; a passing test is.
Step 3: Verify Intent
In addition to checking ACs:
- Check that the implementation truly matches the why in the description. It's easy to meet every AC but miss the intent.
- If there were deviations from the plan, check that they are justified.
Step 4: Summarise
Say whether the review passed or, if not, present a summary of your findings and wait for user input.
Step 5: Wrap Up
Once there are no findings left, or the user has asked you to proceed, remember to set the task status to ready-for-signoff — by default, edit the frontmatter status: field and commit with a (task/NNN) subject suffix; if the project config defines a task-status command, use that instead.
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.
- 1mo ago Changed · +2 tokens per session 839495187f8d
- 1mo ago First seen · 60 lines · 41 tokens per session scan A b9e381342fd9
review-task is a skill published in the GitHub repository patforna/auto-task (11 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 563 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
interrogate
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.