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 cboone/agent-harness-plugins --skill address-reviewgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/address-review)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/address-review"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/address-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 | $0.00074 | $0.01915 |
| Opus 5 | $0.00037 | $0.00958 |
| Sonnet 5 | $0.00015 | $0.00383 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
address-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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address Review
Parse a review document, extract actionable items, and work through them systematically.
Options
The user may provide these options inline:
- --dry-run: Parse and list items without making changes
- --skip <numbers>: Skip specific item numbers (comma-separated, e.g.,
--skip 2,5,8) - --commit-per-item: Commit after each item instead of grouping related fixes
Workflow
1. Identify the Review Document
The user provides a path to a review document, typically as an @-reference or a file path argument. Common locations include docs/reviews/, docs/plans/reviews/, or any markdown file the user references.
Read the file. If the path does not exist, report that and stop.
2. Parse Actionable Items
Extract every actionable item from the review document. Items may appear as:
- Checkboxes:
- [ ] Fix the error handling in auth.go - Unchecked bullets:
- Fix the error handling in auth.go - Numbered lists:
1. Fix the error handling in auth.go - Headings followed by description: A heading that names an issue, with explanatory text below
- Inline code references: Items that reference specific files, functions, or line numbers
For each extracted item, record:
| Field | Description |
|---|---|
| Number | Sequential index (1, 2, 3, ...) |
| Summary | One-line description of the item |
| Type | code-change, documentation, question, or style |
| File hints | Any file paths, function names, or line numbers mentioned |
| Context | The full original text from the review document |
Type classification rules:
- code-change: Mentions fixing, adding, removing, or refactoring code; references specific files or functions
- documentation: Mentions README, docs, comments, docstrings, or documentation files
- question: Phrased as a question or asks for clarification; contains "should we", "consider whether", "why", etc.
- style: Mentions formatting, naming, whitespace, linting, or cosmetic changes
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 · 224 lines · 74 tokens per session scan A 6785efe6f3f0
address-review is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,915 once invoked, about $0.0004 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
code-health
Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela (QA) agent.
review-findings
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification. Delegates to the Forja (Dev) agent.
software-code-refactoring
Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…
01-sdlc
Autonomously orchestrates a request from framing to a draft pull request, isolating implementation, independent review, and final outcome challenge. Use when the user wants to deliver a change end to end. Not for running one development step.
00-async-dev
Drive the async-dev pipeline from one entry point, whether setup, run, or review. Use when the user wants to install async dev, run a ready issue, or address PR review comments, or on a webhook trigger. Not for plain status checks.
05-review
Review a diff read-only on three axes, code, behavior versus the plan, and relevancy, into one verdict report. Use before shipping a change. Not for fixing findings or auditing a codebase.