Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/akolotov/harnessnpx agentmods add skills/akolotov/harness/review-plan-findings-feedbackWrote 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/review-plan-findings-feedback)<a href="https://agentmods.dev/skills/akolotov/harness/review-plan-findings-feedback"><img src="https://agentmods.dev/badge/skills/akolotov/harness/review-plan-findings-feedback/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/review-plan-findings-feedback"><img src="https://agentmods.dev/badge/skills/akolotov/harness/review-plan-findings-feedback.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 | $0.00042 | $0.02257 |
| Opus 5 | $0.00021 | $0.01128 |
| Sonnet 5 | $0.00008 | $0.00451 |
| Haiku 4.5 | $0.00004 | $0.00226 |
Grade A, and why
review-plan-findings-feedback 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 11d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Plan Findings Feedback
Review a follow-up feedback file after plan-review findings were addressed. Do not implement code and do not edit the plan. The only user-facing artifact is a findings file. Adjudication work artifacts may be created only in this run's fresh scratchpad directory.
Inputs And Assumptions
- The user provides the feedback file path, usually
.ai/impl_plans/<plan-id>/findings-feedback/<timestamp>/feedback.md. - The implementation plan path, issue snapshot, and original review findings are expected to already be present in the conversation context because this skill is run in the same session as
implementation-plan-review. - Do not require the user to pass those inputs again. Infer the plan id from the current session first, then from the feedback path if needed.
- Recover the exact issue snapshot used by the original review. Do not silently substitute a newer issue version.
- If the plan id, issue snapshot, or original findings cannot be recovered with confidence, stop and ask for the missing context rather than guessing.
Workflow
1. Resolve The Plan Id
Infer exactly one plan-id, such as issue-418.
Priority:
- The most recent implementation plan path in session context:
.ai/impl_plans/<plan-id>.md. - The feedback file path:
.ai/impl_plans/<plan-id>/findings-feedback/<timestamp>/feedback.md— the plan-id is the first path segment afterimpl_plans/. - Scratchpad paths from the prior review:
.ai/impl_plans/<plan-id>/scratchpads/<timestamp>/...— same rule: the plan-id is the first segment afterimpl_plans/, not a suffix to strip.
Confirm .ai/impl_plans/<plan-id>.md exists before proceeding.
2. Create This Run's Findings Directory First
Every relative path in this skill — scripts, references, templates, and the
../implementation-plan-review/... sibling paths — 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.
What ships with it
3 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.
- 11d ago First seen · 232 lines · 42 tokens per session scan A 39283cefb2c3
review-plan-findings-feedback is a skill published in the GitHub repository akolotov/harness (2 stars, last pushed 11d ago), licensed MIT. It adds 42 tokens to every session and 2,257 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.
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.
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…