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 agentmods add skills/akolotov/harness/implementation-plan-reviewnpx skills add akolotov/harness --skill implementation-plan-reviewgit clone --depth 1 https://github.com/akolotov/harnessWrote 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/akolotov/harness/implementation-plan-review)<a href="https://agentmods.dev/skills/akolotov/harness/implementation-plan-review"><img src="https://agentmods.dev/badge/skills/akolotov/harness/implementation-plan-review.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 | $0.00041 | $0.02443 |
| Opus 5 | $0.00020 | $0.01222 |
| Sonnet 5 | $0.00008 | $0.00489 |
| Haiku 4.5 | $0.00004 | $0.00244 |
Grade A, and why
implementation-plan-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 6d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Plan Review (Expert)
Review an implementation plan for coverage, correctness, and fit with the current codebase. Do not implement.
Inputs
- Implementation plan: a local file path.
- Issue/requirements: either (a) a local file path, or (b) a GitHub issue number (run from the target repo so
ghresolves it).
Every relative path in this skill — scripts, references, and assets — resolves from the directory that holds this
SKILL.md, not from the current working directory. Resolve each one against that directory before running or reading it.
If the user provides a GitHub issue number, prefer fetching it into a local file using the bundled script:
bash scripts/fetch_github_issue.sh <issue-number> --out /tmp/issue.md
Run this command from the skill directory when that directory is inside the target repository. If it is not, keep the
command agent-agnostic by resolving the script path relative to this skill directory while running gh from the target
repo so the issue number resolves against the correct repository.
Fetching is a network operation. When command execution is sandboxed, request
network escalation (require_escalated) for this exact fetch command rather
than granting a reusable broad bash permission. On failure, follow the
script's self-contained ACTION line. It distinguishes unavailable network
(exit 6), credentials unavailable to the process (exit 3), other GitHub
fetch failures (exit 4), and local output failures (exit 5).
Workflow
- Prepare a clean review run:
- Before reading or listing any scratchpad files, run from this skill directory:
bash scripts/new_scratchpads_dir.sh <plan-file>
- Use exactly the absolute path the script printed on stdout as this review's run directory; never glob or guess a path under
scratchpads/yourself. - Each run creates a fresh timestamped directory (
scratchpads/<YYMMDD-HHMM>/); nothing is deleted. Directories from earlier reviews belong to a different run — never read or reuse them for this review. (If the printed path is ever lost from context, the lexicographically-last timestamp subdirectory is the most recent, since the format sorts chronologically — but prefer the printed path.) - If the script fails (non-zero exit;
error: <message>on stderr), stop and report the failure.
What ships with it
9 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.
- agents/openai.yaml 444 B
- assets/finding-adjudication-report.md 2.6 KB
- README.md 718 B
- references/finding-adjudication-protocol.md 5.1 KB
- scripts/_adjudication_report.py 14 KB runs code
- scripts/fetch_github_issue.sh 4.2 KB runs code
- scripts/finalize_adjudication.py 2.2 KB runs code
- scripts/new_scratchpads_dir.sh 2.1 KB runs code
- scripts/verify_adjudication_run.py 3.6 KB runs code
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.
- 6d ago First seen · 228 lines · 41 tokens per session scan A a926be603838
implementation-plan-review is a skill published in the GitHub repository akolotov/harness (2 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 2,443 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.