agentmods.dev

fable5-codex AGENTS.md

Repository instructions for developing and validating the Fable-5 Codex plugin. They describe the preferred working method, evidence requirements, and package rules.

In plain words
What is it for?
Use them when working on Fable-5 tasks such as audits, reviews, fact-checks, design decisions, or broad code sweeps.
Why use it?
They give contributors consistent rules for investigating, changing, and checking work in that repository.

Instructions file for CodexOpenCode

2 12d ago A scan 372 tokens original MIT
View the source file rhein1/fable5-codex
Install

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.

agentmods
npx agentmods add instructions/rhein1/fable5-codex/agents-md
Clone the repo
git clone --depth 1 https://github.com/rhein1/fable5-codex

Made for: Codex, OpenCode.

Per session 372 This file is loaded in full into every session.
When invoked 372 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00372 $0.00372
Opus 5 $0.00186 $0.00186
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash 0c585c10bb7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fable5-codex AGENTS.md 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 2d 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.

AGENTS.md · 31 lines

What it actually says

Fable-5 Repo Instructions

Use this repository to develop and validate the Fable-5 Codex plugin.

Working Method

For substantive engineering tasks, prefer the Fable-5 workflow style:

  1. Map the target before changing it.
  2. Split discovery into independent lenses when the task benefits from broader coverage.
  3. Require evidence for claims: file path, line number when available, and quoted source or observed behavior.
  4. Verify candidate findings adversarially before reporting them as real.
  5. Preserve unknowns, refuted findings, and coverage gaps instead of hiding them.
  6. For audits, reviews, fact-checks, sweeps, and design choices, use the installed Fable-5 Codex skills:
    • $fable-audit
    • $fable-deep-review
    • $fable-fact-check
    • $fable-understand
    • $fable-design-options
    • $fable-sweep

Use real Codex subagents for large or high-risk Fable tasks 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, exhaustive audit, deep review, and broad sweep tasks as large by default. For routine edits, use the rigor rules without spawning extra agents.

Package Rules

  • Keep plugin code under plugins/fable5-codex/.
  • Keep the repo marketplace at .agents/plugins/marketplace.json.
  • Keep marketplace source.path relative and ./-prefixed.
  • Do not introduce absolute user-specific paths into repo docs or marketplace files except in examples clearly labeled as local paths.
  • Run scripts/validate-package.ps1 after changing packaging, skills, schemas, scripts, or custom-agent profiles.
Changes

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.

  1. 2d ago First seen · 31 lines · 372 tokens per session scan A 0c585c10bb7a

Subscribe to this mod's changes

fable5-codex AGENTS.md is an instructions file published in the GitHub repository rhein1/fable5-codex (2 stars, last pushed 12d ago), licensed MIT. It adds 372 tokens to every session, about $0.0019 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.

agent-skillsai-code-reviewcodex-pluginfable5fact-checking
Related

Other instructions, from other repositories

grok-build-codex-plugin AGENTS.md

Instructions for Reederey87/grok-build-codex-plugin, covering repository guidelines, project structure, using grok in codex, commands and style.

Reederey87/grok-build-codex-plugin · 728 tokens

grok-build-codex-plugin CLAUDE.md

Instructions for Reederey87/grok-build-codex-plugin, a project described as: Codex CLI plugin: delegate reviews and bounded coding tasks to the local Grok Build CLI via a bundled MCP server.

Reederey87/grok-build-codex-plugin · 5 tokens

logic-lens GEMINI.md

Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.

hyhmrright/logic-lens · 285 tokens

consult CLAUDE.md

Claude Code instructions for kreek/consult, covering claude.md and pi self-improvement source access.

kreek/consult · 295 tokens

river-review js-ts.instructions.md

Instructions for s977043/river-review, a project described as: レビューを、組織の判断資産へ。Review Judgment as Code for AI-assisted development — codify your team's review standards as repo-owned skills and run them across the SDLC.

s977043/river-review · 130 tokens

lianhuanhua-skills AGENTS.md

Instructions for littlewindy123/lianhuanhua-skills, covering agents.md, project goal, architecture rules, commands and before committing.

littlewindy123/lianhuanhua-skills · 249 tokens