Borrowing it
Nothing to install: this file belongs to sentimony/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/sentimony/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/sentimony/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/sentimony/skills/agents-md)<a href="https://agentmods.dev/instructions/sentimony/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/sentimony/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/sentimony/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/sentimony/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 | $0.01010 | $0.01010 |
| Opus 5.5 | $0.00404 | $0.00404 |
| Sonnet 5.5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
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 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
A public collection of agent skills, published on
skills.sh. Each skill is a directory
skills/<name>/ in the one skills plugin, with SKILL.md and optional
references/, scripts/, examples/. The branch, PR, publish, and test workflow lives in
CONTRIBUTING.md; read it before changing anything in this repository.
Skills
| Skill | Use when |
|---|---|
scope-triage |
a request needs design decisions before code |
plan-crafting |
an approved design needs a multi-step implementation plan |
git-worktree-isolation |
deciding whether work needs an isolated workspace or worktree |
inline-plan-dev |
executing a plan in the current session |
subagent-plan-dev |
executing a plan through coordinated subagents |
parallel-agents |
several units of work might run concurrently through agents |
tdd |
implementing testable behavior changes, test first |
debugging |
investigating bugs, failures, flaky or unexpected behavior |
review-request |
an implementation needs an independent review against its requirements and diff |
cross-review |
a plan or implementation needs review by other agent CLIs (by default the opposite of Codex and Claude Code, plus Antigravity) |
review-resolution |
review findings or PR comments need validation before any fix |
verification-gate |
work is about to be called done, fixed, or mergeable |
branch-finish |
verified work is ready to merge, push, open a PR, or discard |
doc-preview |
a saved request, spec or plan needs an HTML preview and README index entry |
scope-check |
the user invokes the old name or asks about its replacement |
prose-crafting |
drafting or editing English or Ukrainian prose |
dashfix |
writing prose or auditing typographic dashes |
negafix |
writing prose or auditing "it's not just X, it's Y" constructions |
skill-crafting |
designing, creating, evaluating, or retiring agent skills |
echarts |
building or debugging Apache ECharts charts |
frontend-crafting |
building or reviewing user-facing interfaces |
web-debug |
testing or debugging a local web app with Playwright |
vitest |
configuring, writing, or debugging Vitest tests |
typescript |
compiler errors, tsconfig, typing, and module resolution problems |
maintaining-agent-context |
creating or auditing AGENTS.md, CLAUDE.md, and other agent instructions |
secret-hygiene |
using credentials from env files or config with real services |
gh-switch |
a project-scoped gh command is about to run on github.com, or a GitLab API call in a project with a GitLab remote |
commit-all |
the user asks to commit all current changes without a message |
webapp-debugger |
slash-only: testing or debugging a local web app with agent-browser |
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 Changed · +1 lines · +16 tokens per session 4e7e147c826d
- 5d ago Changed · -7 tokens per session 496cd7b56ea3
- 10d ago Changed · -1 lines · -132 tokens per session 2d8cc280e754
- 16d ago Changed · +1 tokens per session fa1cd92eb106
- 18d ago Changed · +2 lines · +53 tokens per session 2e226bbfb325
- 20d ago Changed · +15 tokens per session 88d94701c6a4
- 23d ago Changed · +2 tokens per session aaa9829e3f55
- 24d ago Changed · +7 tokens per session 8231d2086556
- 25d ago Changed · -73 lines · -1,601 tokens per session 93e67189cce6
- 27d ago First seen · 150 lines · 2,656 tokens per session scan A 4d9597dca763
skills AGENTS.md is an instructions file published in the GitHub repository sentimony/skills (7 stars, last pushed 2d ago), licensed MIT. It adds 1,010 tokens to every session, about $0.0040 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.mdsentimony/skills | Instructions file | 7 | 2d ago | MIT | A | 1,010 | 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 |