Borrowing it
Nothing to install: this file belongs to shikanime-labs/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shikanime-labs/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/shikanime-labs/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/shikanime-labs/skills/agents-md)<a href="https://agentmods.dev/instructions/shikanime-labs/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/shikanime-labs/skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/shikanime-labs/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/shikanime-labs/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01621 | $0.01621 |
| Opus 5.5 | $0.00648 | $0.00648 |
| Sonnet 5.5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
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 8d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills
A curated catalog of self-improved agent skills for Hermes and compatible
agents. Each skill lives in its own directory with a SKILL.md.
Language: Markdown (SKILL.md)
Structure
skills/— every catalog skill (org-neutral bodies, org specifics in per-skillreferences/)README.md— Installation and usage documentation
Workflow
One doctrine — the lifecycle is discussion → issue → issue comments → PR.
The issue body is the problem statement with acceptance criteria as a
command-decidable tasklist (the gate ledger); the PR proves it. Skill bodies
are org-neutral; organization-specific conventions load on demand from
per-skill references (references/shikanime.md for shikanime,
references/cloud-pi-native.md for cloud-pi-native console work).
Version Control
Use jj (Jujutsu), not git, for all local work: clone with git clone then
jj git init --git-repo ., develop on bookmarks (jj new main@origin -m "…"), push with jj git push -b <branch>. Fall back to plain git only
where jj is refused by the server (signed annotated tags trip pre_receive
rules — git tag -s + git push origin vX.Y.Z). Fetch before starting:
jj git fetch (stale clones produce empty-diff PRs).
Commit Style
- Plain-text capitalized title, no conventional-commit prefix.
- Body is labeled, one label per line where applicable:
Design:— files or skills the change is grounded in.Related:— companion files, issues, or PRs.Issue: #N— the linked ticket (reference only; the PR↔issue link is Development metadata,sks-pr-triagestep 5).- Free prose explains the atomic change: what and why. Code carries no matching comment — comment only what code structurally cannot say (a workaround's why, an external contract's quirk).
- Footers mandated by policy:
Signed-off-by:— required; commits must be signed (see Protectmain).Change-Id:— keep the originating change's id when amending.
- Nix: dotted assignment (
a.b.c = v;) for a single leaf under a shared parent key; a record literal once two or more keys share the parent, keys sorted - Wrap Markdown lines at 80 columns and run
nix fmtbefore shipping.
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.
- 8d ago Changed · +3 lines · +44 tokens per session fe956e802d29
- 14d ago Changed · +1 lines · +18 tokens per session 7059fc333205
- 16d ago Changed · +5 lines · +97 tokens per session 1e9e27b8c81b
- 28d ago Changed · +1 lines · +22 tokens per session bf450143b4cb
- 1mo ago Changed · +1 lines · +20 tokens per session cd04ef3dd8a6
- 1mo ago Changed · +9 lines · +125 tokens per session 341730a769c4
- 1mo ago Changed · +8 lines · +84 tokens per session 20bb29c4f7d7
- 1mo ago Changed · -7 lines · -184 tokens per session bc1da74b5cf0
- 1mo ago Changed · -6 lines · -61 tokens per session c57af2a1d135
- 2mo ago First seen · 126 lines · 1,456 tokens per session scan A 0ad4585949a3
skills AGENTS.md is an instructions file published in the GitHub repository shikanime-labs/skills (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,621 tokens to every session, about $0.0065 per session on Opus 5.5. 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.
skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills AGENTS.mdshikanime-labs/skills | Instructions file | 2 | 3d ago | Apache-2.0 | A | 1,621 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |