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-deep-reviewnpx skills add rhein1/fable5-codex --skill fable-deep-reviewgit 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-deep-review)<a href="https://agentmods.dev/skills/rhein1/fable5-codex/fable-deep-review"><img src="https://agentmods.dev/badge/skills/rhein1/fable5-codex/fable-deep-review.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 5.1 | $0.00054 | $0.00741 |
| Opus 5 | $0.00027 | $0.00370 |
| Sonnet 5 | $0.00011 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
fable-deep-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable Deep Review
Review like a senior engineer validating a change, not like a summarizer. Default to no edits unless the user asks to address findings.
For ECF-style governed runs, use ../../references/ecf-run-contract.md. For large or high-risk reviews, use real Codex subagents when the runtime exposes a subagent tool and the user has not opted out; treat repo-wide, cross-package, security/privacy/money/data/API, migration, release, or deep-review requests as large by default. Otherwise run single-agent multi-lens and say why no subagents were used. For bot-parseable PR review output, use ../../templates/fable-review-contract.md.
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
- Identify the review target: PR, branch, diff, commit range, or files.
- Restate authority boundaries and declare the ECF run mode:
multi-agentonly with real spawned subagents, otherwisesingle-agent multi-lens. - Read repo instructions and changed files completely before judging them.
- Inspect callers, importers, tests, docs, migrations, and generated/runtime surfaces touched by the change.
- Build a change map: intent, modified behavior, affected contracts, and risk areas.
- Generate candidate regressions from multiple lenses:
- API/contract compatibility
- data/schema and migration safety
- concurrency/idempotency/retry behavior
- auth, privacy, and permission checks
- user-facing/runtime behavior
- test adequacy and missing cases
- Verify each candidate. Prefer a small command or source trace that proves the issue.
- Report only actionable findings. Put open questions after findings.
Subagent Authority
Subagents may map changed files, inspect a review lens, draft candidate findings, or verify candidates. The main agent owns final severity, final findings, edits, commits, pushes, GitHub comments, and PR state changes. If a delegated review pass returns unsupported claims, report them as refuted or unknown rather than treating them as independent agreement.
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 First seen · 54 lines · 54 tokens per session scan A 2d3082127c1e
fable-deep-review is a skill published in the GitHub repository rhein1/fable5-codex (4 stars, last pushed 16d ago), licensed MIT. It adds 54 tokens to every session and 741 once invoked, about $0.0003 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.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.
skeptic
Adversarial code reviewer for Bug Hunter. Rigorously challenges each reported bug to determine if it's real or a false positive. Uses doc-lookup (Context Hub + Context7) to verify framework claims before disproval. The immune system that kills false positives.