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 titusz/skills --skill address-feedbackgit clone --depth 1 https://github.com/titusz/skillsWrote 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/titusz/skills/address-feedback)<a href="https://agentmods.dev/skills/titusz/skills/address-feedback"><img src="https://agentmods.dev/badge/skills/titusz/skills/address-feedback.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 | $0.00203 | $0.02446 |
| Opus 5 | $0.00102 | $0.01223 |
| Sonnet 5 | $0.00041 | $0.00489 |
| Haiku 4.5 | $0.00020 | $0.00245 |
Grade A, and why
address-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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address Feedback
You have a code review and a codebase. Your job is to act on the review responsibly: apply the fixes that are clearly safe, hand the consequential calls back to the user, and leave the result green. The organizing principle is that the reviewer is a witness, not a judge - feedback often comes from an external agent that never saw your plan, the chat history, deliberate design decisions, or the latest code. So every item is a claim to verify against the real code, never an instruction to execute on faith.
Two failures are equally bad and this skill defends against both: applying a wrong or unwanted change because the reviewer said so, and silently dropping a real issue because verifying it was inconvenient. The discipline below - verify, classify, apply-or-escalate, gate - keeps you off both.
Input - get the review
$ARGUMENTS may be: pasted review text, a path or URL to a review file, a PR number/link, or
empty. If empty (a bare /address-feedback, or "address this review" about findings already on
screen), use the most recent code review in the conversation. If you cannot find a review anywhere,
say so and stop - do not invent feedback.
Normalize the review into a numbered list of atomic items. Split bundled comments so each item
makes exactly one claim. Preserve the reviewer's wording and any file:line references - you will
need them to locate the code.
Step 1 - Verify each item against the current code
Trust nothing until you've looked. For each item:
- Locate the exact code it refers to (
Grep/Read). If you can't find it, the review may be stale or about a different branch - note that and lean toward rejecting. - Reproduce the reasoning against reality: can the value actually be null? Is the race reachable?
Is the API truly misused? Read the surrounding context, the callers, the tests, nearby comments,
and
CLAUDE.md/project conventions before believing the claim. - Render a validity verdict: Confirmed (the problem is real), Refuted (the code is actually correct - the reviewer misread or worked from a stale snapshot), or Needs-decision (real only under an assumption or product choice you can't make alone).
- If the claim is right but the reviewer's suggested fix is wrong or suboptimal, fix the real problem - don't paste a bad patch just because a review proposed it.
What ships with it
1 file 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.
- yesterday Changed 093897ecc188
- 7d ago First seen · 186 lines · 203 tokens per session scan A 6eb95d23a0fc
address-feedback is a skill published in the GitHub repository titusz/skills (2 stars, last pushed yesterday), licensed MIT. It adds 203 tokens to every session and 2,446 once invoked, about $0.0010 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…