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/triskweline/skills/agents-mdgit clone --depth 1 https://github.com/triskweline/skillsWrote 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/instructions/triskweline/skills/agents-md)<a href="https://agentmods.dev/instructions/triskweline/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/triskweline/skills/agents-md.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 | $0.00757 | $0.00757 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
skills 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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
A personal collection of Agent Skills. Each skill is a self-contained directory under
skills/<name>/, with its own SKILL.md and whatever references, scripts and tests it
needs.
Commits
Prefix the subject with the skill you worked on, lowercase after the colon:
diff-tour: pack chapters into forks rather than one fork each
self-review: ask the reviewer for a verdict, not a summary
The prefix is what makes git log --oneline readable in a repo where unrelated skills
sit side by side — you can see at a glance which skill a change belongs to, and
git log --oneline | grep '^\w* diff-tour:' is the history of one skill.
A change that is not about one skill takes no prefix: repo-wide housekeeping, the README, this file.
Ignore Python bytecode caches
Write the subject as an imperative describing the change, not the file touched. Don't add a body unless the reason genuinely does not fit in the subject.
A skill's own conventions win
Anything about how a skill works — its procedure, its file layout, how its tests run — belongs in that skill's own documentation, and that documentation is the authority. This file only covers what is true across the repository.
Where a skill has tests, run them before committing a change to it. diff-tour, for
instance, has skills/diff-tour/tests/test_difftour.py.
bin/test-all.sh runs everything: the repo-wide suites under tests/, then each
skill's own suite. It discovers suites rather than listing them, so a new skill's tests
are picked up with no wiring. GitHub Actions runs that same script
(.github/workflows/tests.yml) on every push to main and on every pull request, so
"passes locally" and "passes on CI" are the same command. A branch with no pull request
open gets no CI run, which is the price of never running twice for one push. It needs only python3, git and bash — never add a pip install or a
version manager to either side.
CI deliberately runs a newer Python than this machine, which is the direction that warns you early instead of flattering you. Keep the Python here compatible with both: standard library only, no syntax newer than the oldest interpreter in use.
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.
- 4d ago First seen · 66 lines · 757 tokens per session scan A d7eb5ddc1bbc
skills AGENTS.md is an instructions file published in the GitHub repository triskweline/skills (2 stars, last pushed yesterday), licensed MIT. It adds 757 tokens to every session, about $0.0038 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
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).
langchain AGENTS.md
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.