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 atretyak1985/swarmery --skill sprint-reviewgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/sprint-review)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/sprint-review"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/sprint-review/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/atretyak1985/swarmery/sprint-review"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/sprint-review.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 | $0.00052 | $0.00664 |
| Opus 5.5 | $0.00021 | $0.00266 |
| Sonnet 5.5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
sprint-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A periodic, read-only health pass over everything that changed in the window — finding what slipped through per-change review, without modifying anything.
Method
- Scope first (always): per repo,
git log --since="${SINCE:-14 days ago}",git diff --statagainst the window start,git shortlog -sn. Skip repos with zero commits; the changed-file list scopes every later step. - Fan out reviews (when you can spawn agents): @code-reviewer briefed per dimension (quality, silent failures, contracts) and @security-auditor — each with the scoped file list and "findings as severity + file:line, change nothing". When you cannot spawn, run the passes yourself and note it.
- Check-only suites: typecheck/lint/tests per stack, never with fixes applied; distinguish new failures from known pre-existing ones.
- Report with verdict
## Verdict: PASS | FAIL | PASS WITH BLOCKERS, per-repo activity table, findings by severity, and per-subagent status (COMPLETE | FAILED | SKIPPED). Write it to<workspace>/<project>/workspace/working/{YYYY}/{MM}/sprint-review-{YYYY-MM-DD}.md. FAIL and PASS WITH BLOCKERS are human gates — list the blockers first.
Full phase detail and report template: resources/audit-process.md.
How to use
What it does
Runs the end-of-sprint audit: scopes the window's changes across all project repos, fans out read-only reviewers, runs check-only suites, and writes a dated PASS/FAIL report to the workspace with blockers ranked first.
When to use it
At sprint or milestone boundaries, or before a release cut, when you want a fleet-level look at everything that landed rather than per-PR review.
How to invoke
Load the skill and state the window: "sprint review for the last 14 days" (the default) or an explicit SINCE date. An orchestrator can run it as a standalone task.
Worked example
"Sprint review since 2026-08-18": scoping finds 2 active repos (23 + 7 commits); @code-reviewer and @security-auditor sweep the 61 changed files; suites pass except one known-flaky E2E (noted as pre-existing); report lands at workspace/working/2026/09/sprint-review-2026-09-01.md with ## Verdict: PASS WITH BLOCKERS — one P1 silent failure in a new webhook handler, listed first.
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.
- 1mo ago First seen · 54 lines · 52 tokens per session scan A af97dbf19609
sprint-review is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 664 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 2026-09-03.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
otto-impact-assessment
Check the final diff's consumers, focused tests, evidence, and gaps.
review
Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec compliance check, and decision coverage gate. Produces review.md with decision points. Requires developer approval before $ship can proceed.
factory-self-review
Review and test a Factory work item's pushed branch before any pull or merge request exists, then record the verdict that sends it back to Building or on to open the change request.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
review
Measured code review of a diff, repository, or shortcut debt. Use for code review, PR review, repository audit, or debt inspection with CRAP rows and concrete ranked findings.