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 orenluxy/fable-method --skill full-auditgit clone --depth 1 https://github.com/orenluxy/fable-methodWrote 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/orenluxy/fable-method/full-audit)<a href="https://agentmods.dev/skills/orenluxy/fable-method/full-audit"><img src="https://agentmods.dev/badge/skills/orenluxy/fable-method/full-audit/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/orenluxy/fable-method/full-audit"><img src="https://agentmods.dev/badge/skills/orenluxy/fable-method/full-audit.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 | $0.00116 | $0.01491 |
| Opus 5.5 | $0.00046 | $0.00596 |
| Sonnet 5.5 | $0.00023 | $0.00298 |
| Haiku 4.5 | $0.00012 | $0.00149 |
Grade A, and why
full-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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Audit
Purpose: green tests and a green build are not evidence. A repository accumulates defects that every existing check is structurally blind to — and the checks themselves rot. This runs every applicable lane at once, re-verifies what they claim, and hands back one report the owner decides from.
Reports only. No edit, no commit, no push, no state-changing command. The single exception is starting a local server and running read-only checks. The one file written is the report.
Procedure
-
Baseline, before anything.
git status --porcelain > baseline, record HEAD. RunListAgents(or check for other running sessions): if another session is working this repo, say so up front — its edits will land mid-audit and you must not attribute them to yourself. Give the user a wall-clock estimate as a range, and re-state it if reality moves. -
Detect lanes. Never assume a repo has what yours had. Inspect the tree and pick only what applies:
Lane Runs when How Security always Invoke claude-securityif installed — do not hand-roll a security pass beside it. It computes its own rigor record and verifies findings adversarially. Absent it, run a security lane like the others.Over-engineering always Invoke ponytail-auditif installed. Otherwise skip and say so.Gates any test/lint/CI/check script exists prove-the-gates(this plugin) — including which checks nothing actually runs: a check outside the test script, the push command and CI is a file, not a gateArchitecture always duplicated business rules, layering shortcuts, dead code, framework-specific traps (e.g. conditional hooks), cross-directory imports that packaging misses Calculations a data source exists run the product's own query against the source and compare to what the app returns, metric by metric Content user-facing text exists against the project's own glossary/style rules if it has them; grammar of interpolated numbers; empty and zero states Display a UI and a browser tool exist real browser, real screenshots, two viewports, console must be silent, and hover/click — layered checks never touch the mouse
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.
- 6d ago Changed · +22 tokens per session 5834ebccd623
- 25d ago First seen · 73 lines · 94 tokens per session scan A 2097c8d608ee
full-audit is a skill published in the GitHub repository orenluxy/fable-method (1 stars, last pushed 7d ago), licensed MIT. It adds 116 tokens to every session and 1,491 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 2026-09-19.
Other skills, from other repositories
e2e
Orchestrates e2e testing: BDD scenarios, Playwright autotests. Triggers: e2e tests, BDD scenarios, write autotest.
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
sd-plan-tests
The test-planning craft skill (software-delivery SDLC step 5). Run it AFTER front-authorization has frozen an atom's ACs and BEFORE implementation, to derive a per-AC test plan — happy / edge / negative cases plus the change-attributable baseline case for each pre-change checkpoint — mapped to the acceptance-contract…
eval-forge
Turn an observed agent defect into a machine-checkable eval scenario, generated and self-validated in one step. Use after a defect lands in the feedback ledger, or before changing an agent definition that has no eval coverage. Trigger with /eval-forge.
are-you-done
A completion checker for coding work that asks for evidence before allowing an assistant to say a task is finished.
id-simulate
The infra-delivery OFFLINE LOCAL-SIMULATION step (the new simulate step, between id-test and id-plan) — a PROCEDURE skill the generic agent runs ENTIRELY OFFLINE (no live cloud, no credentials) to author-and-prove the IaC corpus before the live pre-merge plan. Layer 1: apply the profile's EXISTING primitive OpenTofu…