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/autogrammar/todo2code/agents-mdgit clone --depth 1 https://github.com/autogrammar/todo2codeWhat 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 | $0.00617 | $0.00617 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
todo2code 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
AGENTS.md
This target repository follows wellmanifest/new-project policy-as-code.
Before any multi-step implementation, an agent must:
- Read
.governance/manifest.json,TODO.md,project/TICKETS.mdand the active ticket. - Reuse an unfinished ticket whose workstream and scope match. A second active
ticket is allowed only in a distinct workstream with no write-scope overlap.
Otherwise run
./project/new-ticket.sh --title "..." --agent "..." --workstream "...". - Complete the ticket
README.md, ownedai-*.md,intent.jsonandTODO.md. - Stop in
WAIT_FOR_APPROVAL; do not change implementation files yet. - After explicit approval, move to
EDITand stay insideintent.jsonallowedPaths. - Never create or edit
project/ticket-*/user-*.md; only its human owner or a trusted intake boundary may do so. - Keep executable source/tests/scripts outside ticket directories.
- Run
./project/governance-check.shplus the stack and Docker checks before reporting completion. - Serialize ticket-ID allocation before branching, then use a separate
branch/worktree per implementation ticket. Each diff must resolve to exactly
one active ticket. Shared contract paths are edited only by the declared
integration workstream;
integrationTicketcoordinates work but does not transfer path ownership. - Only
IN_PROGRESSreserves a workstream and write scope.BACKLOG,PLANandBLOCKEDretain evidence without blocking another implementation; transition back toIN_PROGRESSbefore changing source or tests. - Treat GitHub review as trusted only when it targets the current HEAD and
either a
Userlogin is in protectedtrusted-reviewersor aBotlogin is in the separate protectedtrusted-validator-appsinput. Never trust an arbitrary Bot review. - Require merge approval evidence to bind repository, PR, current HEAD, active ticket and actor. The protected resolver creates that evidence outside the PR checkout; repository-authored evidence is untrusted.
- A signed attestation is trusted only after a protected verifier validates its signature, issuer, predicate type and subject bindings.
- Validator-agent examples use
LLM_MODEL_VALIDATOR=openrouter/z-ai/glm-5.2; model findings stay advisory. - Configure GitHub with
delete_branch_on_merge=true. A merged ticket branch must disappear after merge. A PR closed without merge keeps its branch until the owner explicitly discards that unmerged work. When no PR is open, the only remote branch is the default branch.
Markdown approval is an audit note, not trusted merge authorization. Required merge approval comes from the repository's protected review, attestation and ruleset boundary.
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 · 49 lines · 617 tokens per session scan A c400cde1172a
todo2code AGENTS.md is an instructions file published in the GitHub repository autogrammar/todo2code (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 617 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 2026-08-31.
Other instructions, from other repositories
plainweave AGENTS.md
AGENTS.md instructions for foundryside-dev/plainweave, covering filigree issue tracker, workflow, at session start, ...or claim a specific issue and do the work, commit, then.
plainweave CLAUDE.md
Claude Code instructions for foundryside-dev/plainweave, covering filigree issue tracker, workflow, at session start, ...or claim a specific issue and do the work, commit, then.
deepagents AGENTS.md
Instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
autoharness AGENTS.md
Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…
cookiecutter-mlops-package AGENTS.md
Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.