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 tomzx/agents --skill learn-from-code-reviewsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/learn-from-code-reviews)<a href="https://agentmods.dev/skills/tomzx/agents/learn-from-code-reviews"><img src="https://agentmods.dev/badge/skills/tomzx/agents/learn-from-code-reviews/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/tomzx/agents/learn-from-code-reviews"><img src="https://agentmods.dev/badge/skills/tomzx/agents/learn-from-code-reviews.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 | $0.00114 | $0.03253 |
| Opus 5.5 | $0.00046 | $0.01301 |
| Sonnet 5.5 | $0.00023 | $0.00651 |
| Haiku 4.5 | $0.00011 | $0.00325 |
Grade A, and why
learn-from-code-reviews 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 22d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Learn From Code Reviews
Mines the review feedback you have received on pull requests you authored, groups it into recurring patterns, and distills those patterns into durable rules stored under $HOME/.sdlc/review-rules/.
The rules are written to be read before design and implementation work, so feedback a reviewer gave once becomes a habit you apply without being told again.
Two jobs:
- Synthesize (default): collect reviews, group them, and merge new rules into the store.
Incremental:
state.jsonrecords the last run, so only new feedback is processed. - Consult (
--consult): print the rules that apply to the current repository, grouped by strength, as a checklist to apply now.
Prerequisites
ghxinstalled and authenticated (readsGH_TOKEN/GITHUB_TOKEN, or falls back togh auth token).- The target repositories are present in the ghx cache.
Run
ghx cache -R <owner>/<repo>first so their PRs and conversation comments are stored; the collector reads PRs and conversation comments from~/.cache/ghx/cache/cache.db(override withGHX_CACHE_DIR) and fetches inline review threads viaghx pr threads. It never calls the GitHub API directly. uvavailable (the collector runs via itsuv run --scriptshebang).- The collector script in this skill directory:
~/.agents/skills/learn-from-code-reviews/scripts/collect_reviews.py.
Scope boundaries
| Skill | Relationship |
|---|---|
handle-pr-reviewer-feedback |
Responds to feedback on open PRs, one PR at a time, to land code. This skill mines historical feedback across PRs to change your future behavior. |
triage-pr-feedback |
Orchestrates the open-feedback response loop on a schedule. Separate concern: it acts, this skill learns. |
create-learnings / run-retrospective |
Reflect on one feature, sprint, or project. This skill reflects on the review record itself across repos. |
improve-sessions |
Mines agent sessions for friction. This skill mines human and bot review feedback for recurring mistakes. |
review-pr |
Performs a review as the reviewer. This skill learns from reviews you received as the author. |
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.
- 22d ago Changed · +10 lines 850eb6bc6594
- 25d ago Changed e2de0161289f
- 27d ago First seen · 240 lines · 114 tokens per session scan A f0ddad660d45
learn-from-code-reviews is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 3,253 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
impl-validator
Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validation of an implementation or generated output.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
agents-md-improver
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…