Borrowing it
Nothing to install: this file belongs to Tsumibito/NavoCMS. 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/Tsumibito/NavoCMS/main/AGENTS.mdgit clone --depth 1 https://github.com/Tsumibito/NavoCMSWrote 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/tsumibito/navocms/agents-md)<a href="https://agentmods.dev/instructions/tsumibito/navocms/agents-md"><img src="https://agentmods.dev/badge/instructions/tsumibito/navocms/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/tsumibito/navocms/agents-md"><img src="https://agentmods.dev/badge/instructions/tsumibito/navocms/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 | $0.00434 | $0.00434 |
| Opus 5.5 | $0.00174 | $0.00174 |
| Sonnet 5.5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
NavoCMS 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NavoCMS agent contract
These rules apply to every automated agent and human contributor in this repository.
Product invariants
- The primary operator interface is an authenticated MCP agent. Focused UI is optional and cannot become the only way to complete a core workflow. One guarantee is deliberately not MCP-only: a human publication decision is recorded through an independent browser confirmation session (ADR 0026); the agent reads the decision and can never issue the receipt.
- Keep the trusted kernel small. Identity, tenant isolation, authorization, event integrity, idempotency, migrations, secrets, quotas, and release policy are not ordinary plugins.
- Plugins request versioned capabilities. They never expand the authority of their caller.
- Every consequential action emits an auditable domain event. Never log hidden model reasoning, credentials, unrestricted PII, or full lead/customer payloads.
- Public publication uses immutable revisions and releases. Approval binds to the exact previewed release hash; stale approval fails closed.
- Canonical prose is portable Markdown plus schema-validated directives. Do not introduce Lexical, arbitrary MDX, or executable HTML as managed content formats.
- Multitenancy is foundational. Every site-owned resource must be tenant- and site-scoped, with database isolation tested independently from application filtering.
- Runtime installation of unreviewed plugin packages by an agent is prohibited.
Contract changes
- Changes to
schemas/require matching specification updates, fixtures, validation tests, and a compatibility note. - Breaking contract changes require a new version; never silently alter an already released schema.
- Architecture changes require an ADR in
docs/architecture/. - Update roadmap gates only when their verification criteria have actually passed.
Working practices
- Prefer small pull requests with one reviewable architectural outcome.
- Preserve unrelated work and never commit secrets, decrypted dotenv files, customer content, or production exports.
- Pin dependencies and GitHub Actions deliberately. Minimize new runtime dependencies.
- Run
pnpm checkbefore proposing a change. - Treat examples as executable contract fixtures, not illustrative pseudocode.
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 · +2 lines · +42 tokens per session cde3903ca7bb
- 2mo ago First seen · 38 lines · 392 tokens per session scan A 864908970fbb
NavoCMS AGENTS.md is an instructions file published in the GitHub repository Tsumibito/NavoCMS (0 stars, last pushed 12d ago), licensed Apache-2.0. It adds 434 tokens to every session, about $0.0017 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 2026-08-31.
NavoCMS AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| NavoCMS AGENTS.mdTsumibito/NavoCMS | Instructions file | 0 | 12d ago | Apache-2.0 | A | 434 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |