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/leifericf/agentic-sdk/agents-mdgit clone --depth 1 https://github.com/leifericf/agentic-sdkWhat 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 | $0.00930 | $0.00930 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
agentic-sdk 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for working on agentic-sdk itself. Read this before changing anything in this repo.
What this is
agentic-sdk is a runtime-agnostic skill system for software development across C, Zig, Clojure, and Elixir. This repo is the source. The authoritative design is docs/design.md; read it first when a change touches architecture, the install model, or the spine.
Layout
skills/<name>/SKILL.md: the atomic skill catalog (flat).skills/shared/holds the cross-cutting doctrine references, not a skill.agents/<name>.md: the 8-agent fleet.src/spine/+mino.edn: the deterministic spine (mino).test/spine/its tests.hooks/: hook templates (master form) plus the shared mino policy.templates/: the projectCLAUDE.mdandgitignoreskeletons.docs/design.md: the spec..opencode/agent/: derived, generated byagentic agents sync; never hand-edit.
This repo keeps its source at the root (skills/, agents/, mino.edn,
src/). The ~/.agentic-sdk/<project>/ home applies to installed projects, not here.
Non-negotiables
- Prose standard. No em-dashes, no ASCII arrows in prose, no process IDs,
terse humanized prose.
agentic lintenforces it; run it before every commit. - No leaks. Never name predecessor or private projects; the maintainer holds the forbidden-token list and it is never written into the public repo, not even as a ban list. No domain framing borrowed from another system. Generalize any product-specific example to the bounded stack plus Functional Core / Imperative Shell.
- Commits. jj-first. One line, category-first imperative subject
(
Skills: ...,Docs: ...,Fix: ...,Build: ...,Refactor: ...,Tests: ...). No body, no AI attribution, no version numbers. Never advance themainbookmark or push without the maintainer's say-so.
Before you commit
mino task test: the spine suite is green.agentic lint $(find docs skills templates hooks -name '*.md'): zero findings.agentic agents check .: the derived OpenCode agents match the masters.- Leak scan:
rg -ni '<forbidden tokens>' skills/ agents/ docs/ templates/ hooks/ src/
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.
- 2d ago First seen · 76 lines · 930 tokens per session scan A 226d4ccda881
agentic-sdk AGENTS.md is an instructions file published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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.
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.
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).
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.