Borrowing it
Nothing to install: this file belongs to dradoaica/cogov-a-sdlc. 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/dradoaica/cogov-a-sdlc/main/.agents/skills/ponytail-review/SKILL.mdgit clone --depth 1 https://github.com/dradoaica/cogov-a-sdlcWrote 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/dradoaica/cogov-a-sdlc/ponytail-review)<a href="https://agentmods.dev/skills/dradoaica/cogov-a-sdlc/ponytail-review"><img src="https://agentmods.dev/badge/skills/dradoaica/cogov-a-sdlc/ponytail-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/dradoaica/cogov-a-sdlc/ponytail-review"><img src="https://agentmods.dev/badge/skills/dradoaica/cogov-a-sdlc/ponytail-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 | $0.00095 | $0.00994 |
| Opus 5.5 | $0.00038 | $0.00398 |
| Sonnet 5.5 | $0.00019 | $0.00199 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
ponytail-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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Ponytail Review (Quality & Lean Code Review)
Purpose
Performs an in-depth, pragmatic code review of proposed changes or pull requests. Evaluates correctness, security, performance under scale, regression testing, and code bloat, providing actionable findings in clear language.
Inputs required
- Diff target: uncommitted changes, specific branch, commit hash, or PR reference.
- Connected codebase context (callers, callees, configuration, and tests).
Preconditions / governance gates
- Advisory Role Only: Review findings inform the human reviewer. Under
.agents/rules/00-no-self-approval.md, this review does not constitute binding approval or merge authorization. - Specification Check: Verify whether changes align with governing ADRs (
docs/adrs/) or User Stories (docs/user-stories/).
Procedure (mandatory)
- Understand context and scope:
- Identify the target changes (uncommitted diff, branch, PR).
- Read surrounding code: callers of modified functions, callees, test suites, and documentation.
- Trace data flow end-to-end (inputs, persistence, outputs).
- Determine the assumed load / scale based on repository configuration and docs.
- Evaluate against quality dimensions:
- Bug: Wrong output, unhandled edge cases (empty collections, zero, bounds, time zones), broken callers.
- Risk: Security vulnerabilities (injection, auth bypass, secret leaks) and data loss risks (unhandled exceptions, lack of transactions).
- Scale: Concurrency bugs, unindexed queries, unbounded in-memory growth, N+1 query loops.
- Missing Test: Risky new logic, security-critical paths, or bug fixes lacking verification tests.
- Speed: Significant algorithmic or I/O bottlenecks.
- Lean (YAGNI): Dead code, redundant abstractions, unnecessary dependencies, duplicate helpers.
- Verify findings against concrete scenarios:
- Ensure every finding describes a concrete, reproducible failure condition ("Input X leads to failure Y").
- Treat shortcut comments as recorded decisions only if they carry a
track:reference (# shortcut: <limit>, <trigger> (risk: ..., track: <US-…|PRB-…>)) and the current load does not violate their ceiling. Report shortcuts withouttrack:asShould fix(undocumented debt,.agents/protocols/maintainability.md→ Technical debt governance). - Propose the minimal fix that deletes or simplifies code rather than adding wrappers.
- Generate structured output:
- What this change does: 2–3 plain English summary sentences.
- Findings: Grouped by priority:
Must fix: Bugs, security vulnerabilities, data loss, scale breakages.Should fix: Risky code without tests, performance regressions, unnecessary code.Nice to have: Micro-optimizations, cleaner syntax.
- Number findings continuously across groups with a 4-part structure: What this is, Problem, Fix, If we skip it.
- Verdict:
Verdict: Ship.orVerdict: fix <numbers> first. - Metrics:
Lean: -<N> lines possible.(if applicable) andNot checked:for unreviewed areas.
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.
- 8d ago First seen · 84 lines · 95 tokens per session scan A 7f4efb88724f
ponytail-review is a skill published in the GitHub repository dradoaica/cogov-a-sdlc (3 stars, last pushed 5d ago), licensed MIT. It adds 95 tokens to every session and 994 once invoked, about $0.0004 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 2026-10-18.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…