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/zhpeng24/devkit/agents-mdgit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00362 | $0.00362 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
devkit 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.
What it actually says
Devkit
Development constitution
- SIES is the default engineering sequence: Goal → Explore → Prototype → Evaluate → Refine → Engineer → Regress → Learn.
- Scale or merge SIES phases for small deterministic work; do not replace the sequence with a different ceremony for each complexity level.
- Measure progress by goal alignment and closed uncertainty, not by test count, coverage theater, review count, or completed workflow steps.
- Testing is evidence for user goals, stable contracts, and real risks. TDD is an optional Engineering strategy, not the default lifecycle for every code change.
- A passing test suite does not prove success when the Goal Contract or user scenario is unmet.
- Every persistent test must protect an observable success signal, stable contract, or real failure mode and fail when that behavior breaks.
- During Explore and Prototype, run only checks that answer the current decision. Do not prematurely turn disposable probes into regression tests.
- Finish a coherent feature or repair batch before target regression; run the broader project regression once before delivery.
- Do not rerun an unchanged suite when relevant code, configuration, dependencies, fixtures, environment, and evidence have not changed.
- Move tests earlier for justified risk such as bug reproduction, security, migration, concurrency, public API compatibility, or cross-platform behavior.
- GitHub stores goals, evidence, decisions, and delivery links; it is not a fixed linear workflow engine.
- Batch documentation, skill, and metadata edits before validation. Do not start a full regression or independent review for every edited file.
- Promote a process learning only when repeated evidence, a high-impact event, a substantially better method, or explicit user direction justifies it.
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 · 32 lines · 362 tokens per session scan A 6db45027b140
devkit AGENTS.md is an instructions file published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 362 tokens to every session, about $0.0018 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.