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/agntdev/skills/agents-mdgit clone --depth 1 https://github.com/agntdev/skillsWhat 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 | $0.01481 | $0.01481 |
| Opus 5 | $0.00740 | $0.00740 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Type
Skill bundle for the agntdev platform. Each skills/<name>/ directory is
a self-contained skill consumable by an agent runtime that supports the
name + description frontmatter protocol (Claude, Cursor, Pi, etc.).
Structure
skills/agnt-cli-builder/— meta-skill, builder's entry pointskills/telegram-bot-*— concept → grammY → toolkit (13 skills total)references/COMMANDS.md(underagnt-cli-builder/) — auto-generated from the agnt-cli repo's oclif manifest. Do not hand-edit.package.json— npm metadata; pinsskill-checkas the validator. Noscripts/directory; validation is delegated to the npm package.
Regenerating the COMMANDS.md reference
The agnt-cli-builder/references/COMMANDS.md file is auto-generated
from the agnt-cli repo's oclif manifest. It is the source of truth for
the command tree the skill teaches agents.
One-shot regen (run from the agnt-cli repo root):
npm run build && npm run prepack && oclif readme --readme-path ../agntdev-skills/skills/agnt-cli-builder/references/COMMANDS.md
This builds the CLI, regenerates oclif.manifest.json (prepack
runs oclif manifest), and emits the regen'd COMMANDS.md into
the skills repo. Never hand-edit references/COMMANDS.md — hand-
edits get clobbered on the next regen. The oclif-generated version
is authoritative (aliases, source links, ordering, exit code notes
all match the runtime).
If you only need to regen against an already-built CLI:
npx oclif readme --readme-path ../agntdev-skills/skills/agnt-cli-builder/references/COMMANDS.md
The corresponding note lives in agnt-cli/AGENTS.md so the CLI side
also knows the regen command.
Note on credential examples. The auto-generated COMMANDS.md
currently shows AGNT-XXXXX-XXXXX and amk_xxxx as literal
connect-code / token examples, because those literals are hardcoded
in agnt-cli/src/commands/connect.ts and login.ts. A v0.18.0
security fix replaced them with <connect-code> / <agent-key>
placeholders in skill bodies, but the CLI source still has the
literals — so they reappear every regen. The right fix is to
update the CLI source itself (a future CLI cut); until then,
expect this drift.
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 · 123 lines · 1,481 tokens per session scan A b8e390528fbe
skills AGENTS.md is an instructions file published in the GitHub repository agntdev/skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,481 tokens to every session, about $0.0074 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.