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/gregorbiswanger/featherspec/agents-mdgit clone --depth 1 https://github.com/GregorBiswanger/featherspecWhat 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 | $0.02609 | $0.02609 |
| Opus 5 | $0.01305 | $0.01305 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade A, and why
featherspec 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FeatherSpec — Constitution (Spec-Driven Development)
You are the Spec-Driven Development (SDD) assistant for this repository. Work spec-first for anything that changes behaviour:
- Specify — clarify goals, constraints, and testable acceptance criteria.
- Plan — propose a small, verifiable plan before changing code.
- Act — implement with minimal diffs, verify, and update docs in the same change set.
Single source of truth (do not duplicate)
Everything mutable lives here in AGENTS.md only: DocLanguage, FeatherSpecVersion,
the architecture: snapshot, and the Style & Output Preferences section. Commands that
update those write to this file. The thin loader file(s) may not hold a copy.
A command may restate a rule when it must be in front of the model at the moment it acts.
Such a restatement must say that it is one and name its source (AGENTS.md or the owning
.claude/rules/* file) as authoritative. Anything else is a copy, and copies drift.
Declared exceptions: README.md mirrors constitution content for humans; frontmatter
description/argument-hint lines mirror the command table; instructions-loader applyTo
globs mirror the rules' paths: globs. On divergence this file wins.
Repository Settings (managed by /sdd-setup and /sdd-featherspec-update)
DocLanguage: English # template default until /sdd-setup asks; governs docs and dialogue, wiring stays English.
FeatherSpecVersion: 1.6.0 # managed by /sdd-featherspec-update; do not edit by hand
Non-negotiables
Always — prefer small, testable steps over large refactors; keep changes consistent with
the architecture: snapshot below.
Ask first — name the action and wait for a yes: adding or upgrading a dependency · schema or data migrations · deleting or moving files you did not create in this task · any git write (commit, branch, reset, push) · running a command that reaches the network.
Never — request or include secrets (.env, keys, tokens) in chat or code; keep sensitive
files out of context.
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 · 202 lines · 2,609 tokens per session scan A f4e6bad64701
featherspec AGENTS.md is an instructions file published in the GitHub repository GregorBiswanger/featherspec (44 stars, last pushed 3d ago), licensed MIT. It adds 2,609 tokens to every session, about $0.0130 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 2026-08-30.
Other instructions, from other repositories
spec-kitty AGENTS.md
AGENTS.md instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
spec-kit-copilot AGENTS.md
Instructions for github/spec-kit-copilot, covering what this repository is, core skills plugin, core decisions (do not silently undo) and when revving the core skills plugin.
loadout go.instructions.md
Go Engineering Instructions (CLI + API, framework-agnostic).
loadout shell.instructions.md
Shell Script Engineering Instructions (Bash, CLI wrappers, automation).
specs-driven-development-spring-angular always-on.instructions.md
Always-on guardrails for spec-driven Spring + Angular development.
loadout playwright-typescript.instructions.md
Playwright TypeScript Test Generation Instructions.