Borrowing it
Nothing to install: this file belongs to epi13/mncs-forge-mcp. 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/epi13/mncs-forge-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/epi13/mncs-forge-mcpWrote 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/epi13/mncs-forge-mcp/agents-md)<a href="https://agentmods.dev/instructions/epi13/mncs-forge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/epi13/mncs-forge-mcp/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/epi13/mncs-forge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/epi13/mncs-forge-mcp/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 | $0.00685 | $0.00685 |
| Opus 5.5 | $0.00274 | $0.00274 |
| Sonnet 5.5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
mncs-forge-mcp 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MNCS Forge agent guidance
- Use Forge for controlled candidate/evidence workflow when a project has a validated
mncs-forge.toml. After modifying candidate content, callcandidate refreshor Control'sforge_candidate_refreshbefore another candidate-scoped evaluation. Refresh registers a successor identity; it does not reuse prior evidence as if it were still current. - Forge does not replace MNCS or MNCDS offline validation and is not required for conformance.
- Modify candidate or generated files only within the declared paths. Never write to contracts, references, evaluators, policies, or protected authorities through Forge.
- Keep MNCS, MNCDS, evidence-class, and promotion statuses separate. Missing or unsupported
evidence remains
UNKNOWN;FAILdominatesUNKNOWN, which dominatesPASS. - Final evaluator-mode results are not repair feedback for the same development epoch.
- Do not claim independence, protected custody, witnessing, governance approval, certification, or promotion from a local Forge result.
- Use Forge provider discovery and capability blockers to select an appropriate declared structural, control-flow, or data-flow provider when a change requires that evidence.
- Source reading, grep, and line counts are review aids, not substitutes for unavailable structural evidence.
- Missing, unsupported, malformed, stale, or unavailable required capability remains
UNKNOWNor a blocker, neverPASS. - When comparative graph-sensitive evidence is claimed, use the same provider, method, scope, and relevant bounds before and after the change.
- Treat suspicious or non-orthodox constructs as requests for bounded evidence, not automatic failures or automatic exceptions. Orthodoxy is a heuristic; declared invariants remain authoritative.
- An intentional-deviation declaration may explain purpose, assumptions, compiler envelope, and
required checks, but it must never suppress, overwrite, or reinterpret a verifier
FAIL. - Keep local invariant results, attack-path reachability, freshness, severity, and workflow
disposition separate. Absence of a demonstrated exploit chain does not convert a confirmed
weakness into
PASS.
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.
- 2mo ago Changed · +22 lines · +249 tokens per session bd684bbefed8
- 2mo ago First seen · 32 lines · 436 tokens per session scan A 5c6d60c74d21
mncs-forge-mcp AGENTS.md is an instructions file published in the GitHub repository epi13/mncs-forge-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 685 tokens to every session, about $0.0027 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.
mncs-forge-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mncs-forge-mcp AGENTS.mdepi13/mncs-forge-mcp | Instructions file | 0 | 1mo ago | Apache-2.0 | A | 685 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | 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 |