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 agentmods add skills/rhein1/fable5-codex/fable-auditnpx skills add rhein1/fable5-codex --skill fable-auditgit clone --depth 1 https://github.com/rhein1/fable5-codexWrote 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/rhein1/fable5-codex/fable-audit)<a href="https://agentmods.dev/skills/rhein1/fable5-codex/fable-audit"><img src="https://agentmods.dev/badge/skills/rhein1/fable5-codex/fable-audit.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 | $0.00075 | $0.01318 |
| Opus 5 | $0.00037 | $0.00659 |
| Sonnet 5 | $0.00015 | $0.00264 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
fable-audit 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable Audit
Run an evidence-first audit. Default to read-only unless the user explicitly asks for fixes.
For ECF-style governed runs, use the plugin reference at ../../references/ecf-run-contract.md and the starter template at ../../templates/fable-ecf-run-contract.json. The contract records scope, authority, required lenses, delegation policy, authority split, evidence policy, verification policy, and the final receipt. It does not itself spawn subagents.
For large or high-risk Fable tasks, recommend running the parent task on gpt-5.6-sol with Ultra (model_reasoning_effort = "ultra") when available. Ultra may delegate proactively, but still explicitly request parallel delegation for disjoint Fable lenses when the runtime supports subagents; otherwise use single-agent multi-lens and report the reason.
Workflow
- Restate scope, focus, and any authority boundaries.
- Declare the run mode:
multi-agentonly when real subagents will be spawned, otherwisesingle-agent multi-lens. - Declare the ECF run contract inline or as an artifact when the user asks for ECF, subagents, repeatable evidence, CI ledgers, or durable receipts.
- Read repo instructions before source files. Follow stricter local policy.
- Map the target: entrypoints, public APIs, data stores, config, tests, docs, deployment hooks, and callers/importers.
- Run independent lenses:
- correctness and edge cases
- integration wiring and call contracts
- security, privacy, and authz/authn
- data consistency, persistence, idempotency, and migrations
- operational behavior, startup, observability, and fail-closed paths
- test coverage and docs-vs-reality
- Create candidate findings with a concrete failure scenario and exact evidence.
- Verify each candidate before reporting it. Try to reproduce, refute, or bound it with source reads and commands.
- Preserve rejected or uncertain candidates in a short "Not Reported" or "Unknowns" section when they materially affect confidence.
- Report findings first, ordered by severity. Keep summary secondary.
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.
- 4d ago First seen · 87 lines · 75 tokens per session scan A 624e03678a01
fable-audit is a skill published in the GitHub repository rhein1/fable5-codex (4 stars, last pushed 14d ago), licensed MIT. It adds 75 tokens to every session and 1,318 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
grok-build-delegate
Use the local Grok Build CLI for second-opinion reviews, adversarial critiques, or delegated read-only investigation from Codex.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.