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 arishofmann/opus-to-fable --skill fable-reviewgit clone --depth 1 https://github.com/arishofmann/opus-to-fableWrote 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/arishofmann/opus-to-fable/fable-review)<a href="https://agentmods.dev/skills/arishofmann/opus-to-fable/fable-review"><img src="https://agentmods.dev/badge/skills/arishofmann/opus-to-fable/fable-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/arishofmann/opus-to-fable/fable-review"><img src="https://agentmods.dev/badge/skills/arishofmann/opus-to-fable/fable-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 | $0.00093 | $0.00488 |
| Opus 5 | $0.00046 | $0.00244 |
| Sonnet 5 | $0.00019 | $0.00098 |
| Haiku 4.5 | $0.00009 | $0.00049 |
Grade A, and why
fable-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 9d 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.
What it actually says
Fable Review — adversariale Selbst-Verifikation
Lies dein eigenes Ergebnis so, wie es ein skeptischer Reviewer täte, der einen Fehler finden will — nicht, um die eigene Arbeit zu bestätigen.
Checkliste
- Korrektheit: Tut der Code / das Ergebnis wirklich, was verlangt war? Zeile für Zeile gegen die Anforderung prüfen.
- Error-/Edge-Cases: leere Eingaben, null/undefined, Grenzwerte, Nebenläufigkeit, Fehlerpfade — nicht nur der Happy Path.
- Annahmen: Welche unausgesprochenen Annahmen trägt die Lösung? Welche davon ist unbelegt?
- Belege: Jede wichtige Behauptung — was ist die Evidenz? Was würde sie widerlegen?
- Regressionen: Bricht die Änderung etwas Bestehendes? Wurde etwas übersehen oder nur halb erledigt?
- Ehrlichkeit: Deckt sich ein "fertig/getestet" mit dem tatsächlichen Output (z. B. echten Testläufen)?
Vorgehen
- Gehe die Checkliste konkret durch und notiere gefundene Schwächen (mindestens eine).
- Fixe, was du fixen kannst; flagge den Rest klar und ehrlich dem Nutzer.
- Für hohe Sicherheit: starte 2–3 unabhängige Prüfer-Sub-Agenten (Agent-Tool), jeder mit dem Auftrag, die Lösung zu widerlegen — je eine Linse (Korrektheit / Sicherheit / Edge-Cases). Übernimm nur, was Mehrheit bzw. Belege standhält.
Haltung
Ziel ist, die eigene Arbeit zu brechen, bevor es der Nutzer oder die Produktion tut. Lieber eine echte Schwäche offen benennen als falsche Sicherheit ausstrahlen.
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.
- 9d ago First seen · 35 lines · 93 tokens per session scan A 6513876f2c47
fable-review is a skill published in the GitHub repository arishofmann/opus-to-fable (2 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 488 once invoked, about $0.0005 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…