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 carsteneu/yesmem --skill risk-based-code-reviewgit clone --depth 1 https://github.com/carsteneu/yesmemWrote 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/carsteneu/yesmem/risk-based-code-review)<a href="https://agentmods.dev/skills/carsteneu/yesmem/risk-based-code-review"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/risk-based-code-review/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/carsteneu/yesmem/risk-based-code-review"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/risk-based-code-review.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 | $0.00052 | $0.04521 |
| Opus 5.5 | $0.00021 | $0.01808 |
| Sonnet 5.5 | $0.00010 | $0.00904 |
| Haiku 4.5 | $0.00005 | $0.00452 |
Grade A, and why
risk-based-code-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 14d 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risikobasierte Softwareprüfung
Zweck
Prüfe Änderungen nach möglicher Auswirkung, nicht nach Zeilenzahl. Der Katalog ist kein Pflichtprogramm: Wähle zuerst eine Stufe, führe deren Pflichtkern aus und ergänze nur die ausgelösten Fachmodule.
Wann der Skill gilt
Nutze ihn:
- vor einer Abschluss-, Merge-, Release- oder Deployment-Aussage,
- bei Code-Reviews und Abnahmen,
- nach Fehlerkorrekturen und funktionalen Änderungen,
- bei unklarer Testtiefe,
- immer bei Sicherheits-, Daten-, Migrations- oder Betriebsrisiken.
Nicht nötig ist der volle Skill für reine Fragen ohne Änderung. Bei einer reinen Textkorrektur genügt Stufe 1.
1. Prüfstufe bestimmen
Entscheidend ist der schlimmste plausible Schaden. Im Zweifel eine Stufe höher wählen.
Stufe 1 – Minimal
Gilt nur, wenn alle Aussagen zutreffen:
- Änderung ist lokal und leicht rückgängig zu machen.
- Kein ausführbares Verhalten, Vertrag, Build-Artefakt oder generierter Inhalt ändert sich.
- Keine Sicherheits-, Daten-, Berechtigungs-, Migrations- oder Produktionswirkung.
Typisch: Rechtschreibung, Kommentare, nicht ausführbare Dokumentation, isolierte Darstellung ohne Logik.
Pflicht:
- Exakten Diff und Arbeitsbaum prüfen.
- Geänderten Inhalt bzw. die Darstellung direkt prüfen.
- Eine unmittelbar auf die geänderte Datei bezogene Schnellprüfung ausführen, sofern das Projekt eine solche bereits bereitstellt; keinen projektweiten Lint nur dafür einführen.
- Unbeabsichtigte Änderungen und Geheimnisse ausschließen.
Nicht automatisch nötig: vollständige Suite, Browsermatrix, Backup, Migration, Deployment.
Stufe 2 – Standard
Gilt, wenn Verhalten oder Zusammenspiel geändert wird, aber kein Hochrisiko-Auslöser vorliegt.
Typisch: Geschäftslogik, normale API-/UI-Erweiterung, Persistenz in bestehendem Schema, Abfragen, mehrere Komponenten.
Pflicht:
- Alles aus Stufe 1.
- Anforderung und Akzeptanzkriterium festhalten.
- Positiv-, Negativ- und relevanten Fehlerfall testen.
- Betroffene Unit-/Integrations-/Schnittstellentests ausführen.
- Relevante Regression-Suite ausführen.
- Persistenz, Zustandsübergänge und Berechtigungen prüfen, falls berührt.
- Saubere, reproduzierbare Testumgebung verwenden.
- Benutzerablauf real im Browser prüfen, falls UI berührt.
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.
- 14d ago First seen · 381 lines · 52 tokens per session scan A eea768166c3a
risk-based-code-review is a skill published in the GitHub repository carsteneu/yesmem (45 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 4,521 once invoked, about $0.0002 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 2026-10-02.
Other skills, from other repositories
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.
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.
agent-pipeline
Turn a review of code or docs into verified, actioned work with tiered agents. A cheap agent maps, a smart agent tags findings with predicted steps and a test written before any action, a skeptic verifies, a cheap agent acts in a sandbox, and the whole chain is reviewed afterwards with agent-review. Use for a sweep…
quality
PALADIN quality gatekeeper. Two-stage system: Stage 1 checks spec compliance (pass/fail, blocks everything on failure). Stage 2 scores project health 0-100 across 6 tiers. Issues verdict: SHIP IT / SHIP WITH CAUTION / NOT READY / BLOCKED. Evidence Before Claims: every finding must cite the file, line, and what was…
gitzoid-fix
Fix GitZoid's findings on a pull request in a loop - read them over MCP, fix, test, push, wait for GitZoid's review of the new commit, repeat until clean (at most 3 rounds). Use when asked to fix GitZoid findings or make a PR pass GitZoid.
workflow-evidence-audit
Use when auditing validation workflow evidence before a maintainer review or diagnostic handoff.