Borrowing it
Nothing to install: this file belongs to SchmiedmayerLab/heartwood. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SchmiedmayerLab/heartwood/main/AGENTS.mdgit clone --depth 1 https://github.com/SchmiedmayerLab/heartwoodWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/schmiedmayerlab/heartwood/agents-md)<a href="https://agentmods.dev/instructions/schmiedmayerlab/heartwood/agents-md"><img src="https://agentmods.dev/badge/instructions/schmiedmayerlab/heartwood/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/schmiedmayerlab/heartwood/agents-md"><img src="https://agentmods.dev/badge/instructions/schmiedmayerlab/heartwood/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.02214 | $0.02214 |
| Opus 5.5 | $0.00886 | $0.00886 |
| Sonnet 5.5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
heartwood 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 1mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS Instructions
Guidance for contributors working in this repository.
Purpose
This file is the repository orientation and rule set. It should point to the canonical docs instead of restating them.
When project direction changes, update the relevant architecture or operations page first, then update this file only if routing or durable working rules change.
Canonical Documentation
| Need | Source |
|---|---|
| Repository summary | README.md |
| Published documentation home and user journey | documentation/index.md |
| First-use installation, project, model, and interface flow | documentation/start/index.md |
| Workstation, Terra, Carina, and managed-environment selection | documentation/platforms/index.md |
| Installation routes | documentation/start/install.md |
Project boundary, persistence, and .heartwood/ layout |
documentation/start/project.md |
| Research-environment, hosted, compatible-service, and Heartwood-managed model workflows | documentation/models/index.md |
| Deployment responsibilities, standard environment records, pilot evaluations, and platform extension contract | documentation/operate/index.md |
| Heartwood–platform ownership boundary and platform requirements | documentation/operate/platform-contract.md |
| Release support, compatibility, and deprecation policy | documentation/operate/support.md |
| Browser workflow | documentation/use/browser.md |
| Research specialist roles and boundaries | documentation/use/specialists.md |
| Research workflow setup, stage checks, and review | documentation/use/research-workflows.md |
| Command reference | documentation/reference/cli.md |
| Readiness states, stable diagnostics, and recovery steps | documentation/reference/troubleshooting.md |
| Qualified GPU runtime, model, and platform combinations | documentation/reference/gpu-compatibility.md |
| Product boundaries and durable technical rationale | documentation/architecture/index.md |
| Project, gateway, adapter, interface, and data-flow architecture | documentation/architecture/system.md |
| Security and controlled-data responsibilities | documentation/operate/security.md |
| Authoritative audit exports, signing, and retention | documentation/operate/audit-checkpoints.md |
| Audit integrity and session persistence | documentation/architecture/sessions-audit.md |
| Scientific experiment records, lineage, and recovery | documentation/architecture/experiments.md |
| Skill trust, distribution, activation, and interface contract | documentation/architecture/skills.md |
| Research Skill contribution, policy, and validation | documentation/contribute/skills.md |
| Testing layers and evidence language | documentation/architecture/testing.md |
| Python and web development workflow | documentation/contribute/development.md |
| Pull request description structure | Organization pull request template |
| Planned implementation, acceptance criteria, and delivery status | GitHub Issues and the Heartwood Project |
| Acronyms and specialized terms | documentation/reference/glossary.md |
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.
- 1mo ago Changed · +1 lines · +35 tokens per session e85759b4de53
- 1mo ago Changed · +2 lines · +57 tokens per session 04f89344a1c4
- 2mo ago First seen · 106 lines · 2,122 tokens per session scan A 27c5bbdde738
heartwood AGENTS.md is an instructions file published in the GitHub repository SchmiedmayerLab/heartwood (11 stars, last pushed yesterday), licensed MIT. It adds 2,214 tokens to every session, about $0.0089 per session on Opus 5.5. 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.
heartwood AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| heartwood AGENTS.mdSchmiedmayerLab/heartwood | Instructions file | 11 | yesterday | MIT | A | 2,214 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |