Borrowing it
Nothing to install: this file belongs to camthink-ai/NeoMind. 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/camthink-ai/NeoMind/main/AGENTS.mdgit clone --depth 1 https://github.com/camthink-ai/NeoMindWrote 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/camthink-ai/neomind/agents-md)<a href="https://agentmods.dev/instructions/camthink-ai/neomind/agents-md"><img src="https://agentmods.dev/badge/instructions/camthink-ai/neomind/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/camthink-ai/neomind/agents-md"><img src="https://agentmods.dev/badge/instructions/camthink-ai/neomind/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 | $0.04379 | $0.04379 |
| Opus 5.5 | $0.01752 | $0.01752 |
| Sonnet 5.5 | $0.00876 | $0.00876 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
NeoMind 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development coordination
Read CLAUDE.md and the relevant module documentation before changes.
Current work is coordinated by Codex (2026-11-02): summary preservation, default chat loop exits, and skill search isolation. Do not start overlapping eval chains or edit these same files concurrently. Keep existing run artifacts; use unique output directories.
Use Spark-1.7B for primary acceptance with fixed model/runtime/sampling settings. Keep hardware-specific baselines separate.
Do not put credentials in source or logs. Do not commit, push, deploy, or publish without an explicit user instruction.
Follow the agent evaluation method for ongoing improvements.
Active comprehensive evaluation (2026-11-03)
A frozen three-arm full-regression study is running. Root /tmp/neomind-comprehensive-20261103-085034, official data main/, controller /tmp/neomind-comprehensive-single-run.py PID38647 (verify before acting). 69 IDs, both languages, two rounds, three Release versions =828 trials. Fixed Spark32K single-slot, thinking enabled, .3/.75/20, 600s case cap. Do not start overlapping inference/builds or revive older queues. Four-slot root data is a capacity pilot, not official results. Binaries/evaluator/fixtures/grader are frozen; live workspace source remains untouched. External GLM export of evaluation answers/evidence for semantic judging was rejected by automatic approval review; sender was not run. Do not bypass it. Use local task/state and trace metrics; do not claim universal factuality judging. No commit, push, deploy or publish.
Comprehensive local audit final helper: PID45773 (verify), analysis/ archived with manifest, 7 audit tests and 6 pairing tests pass. Native hard signals are independently recomputed from frozen case+record, not just copied. Final comprehensive-report.md is emitted only after all828 and hash checks pass. Pilot orphan API processes were cleaned; official controller PID38647 remains active.
Takeover by Mac-local GLM (2026-11-03, ~14:10) — corrects the stale process notes above
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 · 199 lines · 4,379 tokens per session scan A 96658bfe1219
NeoMind AGENTS.md is an instructions file published in the GitHub repository camthink-ai/NeoMind (60 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,379 tokens to every session, about $0.0175 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 2026-11-06.
NeoMind AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| NeoMind AGENTS.mdcamthink-ai/NeoMind | Instructions file | 60 | yesterday | Apache-2.0 | A | 4,379 | 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 |