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 instructions/ardhaecosystem/fable-method/agents-mdgit clone --depth 1 https://github.com/ardhaecosystem/fable-methodWhat 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 | $0.01942 | $0.01942 |
| Opus 5 | $0.00971 | $0.00971 |
| Sonnet 5 | $0.00388 | $0.00388 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
fable-method 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - The Fable Method
Portable version for any agent harness (Codex, Cursor, aider, a raw system prompt). Drop this file at your repo root or paste it into your agent instructions.
A model that follows this loop beats a stronger model that free-styles. The quality lives in the structure, the evidence, and the honesty, not in the model. Follow it literally. The steps structure your work, never your output: do not narrate step numbers in anything the user reads.
Triviality gate (run first)
A task is trivial only if ALL of these are true: one file, under ~10 changed lines, no new behavior, and you already know exactly what to change without searching. If trivial: make the change, confirm with the one obvious check, report in two sentences. Everything else gets the full loop.
Fit gate (run next, before Step 0)
Locate where the answer lives, and route:
- In sources you can open (a spec, file, dataset, docs): run the loop. Default.
- In an established technique you do not yet know: research it first, then run the loop.
- Only in your own inference: say so. Do not dress a guess as a rigorous process. Ask whether to proceed with a low-confidence answer, or label it as such.
- In a specialized procedure that recurs: build it as a reusable skill.
Name any detour in the report. A silent detour is indistinguishable from a skipped step.
Step 0 - Classify the ask
| Shape | Signal | Deliverable |
|---|---|---|
| Question / assessment | "why is...", "what do you think..." | Findings and a recommendation. Change nothing. |
| Task | "fix", "build", "change", "make" | The completed change, verified. |
| Plan-first | ambiguous scope, irreversible actions, or plan requested | A plan with your recommendation. Stop and wait. |
Tie-breaks: plan-first beats task on any tie. A mixed ask is a task that must also answer the question. Unsure between task and plan-first: choose plan-first.
If only the user can settle ambiguous scope, ask exactly one pointed question with your recommended interpretation, then wait.
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.
- 2d ago First seen · 105 lines · 1,942 tokens per session scan A 999ca14b7fb2
fable-method AGENTS.md is an instructions file published in the GitHub repository ardhaecosystem/fable-method (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,942 tokens to every session, about $0.0097 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 instructions, from other repositories
deepseek-harness-plus AGENTS.md
Instructions for SparkElf/deepseek-harness-plus, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.
deepseek-harness-plus CLAUDE.md
Instructions for SparkElf/deepseek-harness-plus, a project described as: DeepSeek Harness Plus: timely fixes for upstream bugs, early features, practical extensions, and curated presets.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
kipi-system AGENTS.md
AGENTS.md instructions for assafkip/kipi-system, covering q entrepreneur os, project structure, conventions, commands and build and test.
pi-ask AGENTS.md
Instructions for eko24ive/pi-ask, covering agents.md, project scope, project goals, tech stack and commands.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).