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 akolotov/harness --skill save-review-commentsgit 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/save-review-comments)<a href="https://agentmods.dev/skills/akolotov/harness/save-review-comments"><img src="https://agentmods.dev/badge/skills/akolotov/harness/save-review-comments/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/akolotov/harness/save-review-comments"><img src="https://agentmods.dev/badge/skills/akolotov/harness/save-review-comments.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 | $0.00040 | $0.01196 |
| Opus 5 | $0.00020 | $0.00598 |
| Sonnet 5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
save-review-comments 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 9d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Review Comments
Persist only the surviving actionable review comments/findings of the current session. Do not include rejected or refuted candidates, general summaries, coverage notes, or test strategy, unless one of those is itself an actionable finding.
Path Conventions
Paths in this document use <SKILL_DIR> to mean this skill's installation directory — for
example .claude/skills/save-review-comments in Claude Code, or
.codex/skills/save-review-comments in Codex CLI. Whenever you see <SKILL_DIR> in a Bash
invocation, substitute the actual installation path resolved from the harness. Do not
synthesize an absolute path from your own filesystem assumptions.
Review Types
This skill serves two review types. They never share an identifier or an output path, so determine the type first, from the session context, and then follow only that branch.
| Review type | Identifier | Source of the identifier |
|---|---|---|
| Implementation-plan review | plan-id |
the implementation plan file path |
| Code review | pr-id |
the numeric GitHub PR id |
- Implementation-plan review requires the plan file path. The
plan-idis the plan file's stem, and the output goes next to the plan itself — no issue needs to exist for the plan, and the plan does not need to live under.ai/impl_plans. If the path is not known, ask the user. - Code review requires a numeric GitHub PR id. If it is not known, ask the user. Do not fall back to a branch name.
Workflow
-
Determine the review type and its identifier, as described above.
-
Create this run's output directory with the bundled script. Run exactly one of:
<SKILL_DIR>/scripts/new_comments_dir.sh --plan-file <plan-file><SKILL_DIR>/scripts/new_comments_dir.sh --pr-id <numeric-pr-id>
What ships with it
4 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.
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.
- 9d ago First seen · 116 lines · 40 tokens per session scan A e21c852d67b5
save-review-comments is a skill published in the GitHub repository akolotov/harness (2 stars, last pushed 8d ago), licensed MIT. It adds 40 tokens to every session and 1,196 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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…