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/djscheuf/agentic-dev-ecosystem-template/agents-mdgit clone --depth 1 https://github.com/djscheuf/agentic-dev-ecosystem-templateWhat 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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
agentic-dev-ecosystem-template 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault Protocol
This repo maintains a compounding vault/ of project knowledge. The vault is the
first place you look and the last place you write.
At Session Start
- Read
vault/INDEX.mdto see what's documented. - If the task touches a topic with an existing vault page, read it BEFORE reading source code.
- If the task touches a topic WITHOUT a vault page, note it — you'll write one at the end.
During the Session
- When you encounter something non-obvious (a gotcha, a decision, a pattern):
- Check if
vault/has a page for it. If yes, do not re-discover it. - If no, note it for end-of-session capture.
- Check if
- Never cite internal knowledge the user can't verify. If it's not in
vault/, don't claim it as fact.
At Session End
When the session produced a decision, solved a non-obvious problem, or established a pattern:
- Write a vault page. Location rules (match the directories that exist in this repo's
vault/):- Decisions (why we chose X over Y) →
vault/decisions/ADR-NNN-<slug>.md(next sequential number) - Postmortems →
vault/incidents/<YYYY-MM-DD>-<slug>.md - Service/component notes, runbooks, gotchas →
vault/services/<service>.md - Personas →
vault/personas/<name>.md - Cross-cutting topic hubs →
vault/moc/<topic>.md(a "Map of Content" that links related pages) - Glossary entries → append to
vault/glossary.md
- Decisions (why we chose X over Y) →
- Update
vault/INDEX.mdto link the new page. - One page per topic. If a page grows > 300 lines, split it (same threshold as
vault/INDEX.md).
Writing Style
- Plain markdown. No front-matter unless required by another tool.
- Lead with the bottom line: the answer in the first 2 lines, details below.
- Use the present tense for current state ("we use Redis") and past tense for history ("we tried DynamoDB, it didn't fit").
- Include dates on decisions — these age, and agents need to know how fresh a claim is.
- No prose walls. Headers, lists, tables, code blocks.
Never
- Put secrets in
vault/. It's git-tracked — assume public. - Put PII in
vault/. Same reason. - Write vault pages that duplicate code comments. The vault is for things code can't express.
- Leave
vault/INDEX.mdout of date. The index is the API.
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 · 51 lines · 612 tokens per session scan A 723880d63462
agentic-dev-ecosystem-template AGENTS.md is an instructions file published in the GitHub repository djscheuf/agentic-dev-ecosystem-template (12 stars, last pushed 2d ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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 2026-08-30.
Other instructions, from other repositories
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.
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).
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.