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/bitflight-devops/skilllint/agents-mdgit clone --depth 1 https://github.com/bitflight-devops/skilllintWhat 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 | $0.03248 | $0.03248 |
| Opus 5 | $0.01624 | $0.01624 |
| Sonnet 5 | $0.00650 | $0.00650 |
| Haiku 4.5 | $0.00325 | $0.00325 |
Grade A, and why
skilllint 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 yesterday.
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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Universal working rules for repository tasks. Project-specific instructions override these where they conflict.
Before Editing
- Define success. State the required outcome, acceptance criteria, preserved behavior, constraints, and non-goals.
- Establish the boundary. Identify owners, consumers, inputs, outputs, dependencies, interfaces, and affected environments.
- Separate evidence from inference. Current code, tests, file placement, wiring, counts, versions, and other observed state describe what exists; they do not prove intended ownership, durable design intent, or the correct change location.
- Surface consequential uncertainty. State assumptions and competing interpretations. Resolve uncertainty that could change scope, compatibility, ownership, or architecture before editing.
- Choose the smallest viable change. Prefer existing abstractions and established dependencies over new code. Compare viable approaches by evidence, blast radius, trade-offs, maintenance cost, and reversibility.
Claims and Evidence
The rules above govern changes. These govern statements — in a reply, an issue, a commit message, a code comment, or a brief handed to a subagent.
- A claim about the world needs a command. Do not state a fact about this codebase, another repository, a library, or a tool's behavior unless something run in the current session established it. Where no check was run, mark the claim unverified in the same sentence.
- A subagent's characterization is not evidence. It is a claim with the same standing as your own. Check the artifact it describes before repeating it or building on it.
- Contradicting evidence stops the work. An empty grep, a truncated capture, a result that disagrees with the plan already in flight — resolve it before continuing. These are the cheapest signals available and the easiest to walk past.
- An unverified claim that reaches an issue, a commit, or a comment becomes a premise. Later readers cannot distinguish it from a checked fact and will cite it as one. Correcting the claim later does not retract the work built on it — revisit that too.
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.
- yesterday First seen · 276 lines · 3,248 tokens per session scan A 6001fc5d3b85
skilllint AGENTS.md is an instructions file published in the GitHub repository bitflight-devops/skilllint (6 stars, last pushed 2d ago), licensed MIT. It adds 3,248 tokens to every session, about $0.0162 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.