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/srinitude/skills/agents-mdgit clone --depth 1 https://github.com/srinitude/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/srinitude/skills/agents-md)<a href="https://agentmods.dev/instructions/srinitude/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/srinitude/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 | $0.01445 | $0.01445 |
| Opus 5 | $0.00723 | $0.00723 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
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 3d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository rules
Goal
Build and publish portable Agent Skills from one canonical skill tree.
Every supported client must load the same skill bytes.
This file is the one rule set for the repository and its skills. It merges the
original repository rules with the generation contract that ships inside
skills/skill-factory/references/generation-contract.md. Where the two rule
sets conflicted, the generation contract's rule holds, with two exceptions
recorded below: the description limit follows the agentskills.io specification,
and new skills start at metadata.version: "0.1.0".
Source layout
skills/<name>/SKILL.mdowns each skill body.- Put optional detail in
references/, executable code inscripts/, worked examples inexamples/, and evaluation inputs inevals/. - A skill may also bundle
assets/templates, tests inscripts/tests/, and its ownmise.tomltask graph so it verifies itself with its ownmise run ci. - Keep file references relative to the skill root and at most one subdirectory deep.
- Don't copy a skill body into a client integration.
- Put generated local output only in
.artifacts/.
Skill contract
- Follow every current page listed in
evidence/agentskills-pages.json. - Each skill directory name must equal its frontmatter
name. - Registry skill names use lowercase letters, digits, and single hyphens. The limit is 64 characters. Skills generated for use outside this registry may use the wider generation-contract pattern
^[a-z0-9][a-z0-9._-]*$. - Descriptions are non-empty and at most 1024 characters, the agentskills.io limit.
- Descriptions start with
Use when, state when the skill applies, and carry the keywords a user would type. They must not summarize the skill's procedure. metadata.authorisKiren Srinivasan.- New skills start at
metadata.version: "0.1.0". - Each skill owns its version. It must not depend on a package, integration, GitHub release, or another skill version.
- Metadata values are strings.
- Keep
SKILL.mdbelow 200 lines. Move optional detail out before 150 lines. - Tell the reader exactly when to load each reference.
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.
- 3d ago First seen · 121 lines · 1,445 tokens per session scan A e824f56d7ce0
skills AGENTS.md is an instructions file published in the GitHub repository srinitude/skills (2 stars, last pushed yesterday), licensed MIT. It adds 1,445 tokens to every session, about $0.0072 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
manifest CLAUDE.md
Claude Code instructions for mnfst/manifest, covering manifest development guidelines, what manifest is, important: cloud mode always, 1. ensure the postgresdb container is running and 2. create a pristine database with a unique name.
manifest AGENTS.md
AGENTS.md instructions for mnfst/manifest, covering manifest agent guidelines and domain terminology.
clawdi AGENTS.md
AGENTS.md instructions for Clawdi-AI/clawdi, covering clawdi, oss boundary, repository map, local end-to-end and verification.
BootAgent AGENTS.md
AGENTS.md instructions for MaimoryLab/BootAgent, covering bootagent 开发约定, 目录, 本地命令, codegraph and 代码边界.
clawdi CLAUDE.md
Claude Code instructions for Clawdi-AI/clawdi: The canonical repo-wide agent instructions live in AGENTS.md.
simmer-sdk AGENTS.md
Instructions for SpartanLabsXyz/simmer-sdk, covering agents.md — simmer sdk, this repo is public, currency formatting, live is a constructor arg, not a per-trade flag and market discovery is recency-windowed.