Borrowing it
Nothing to install: this file belongs to ProAgentStore/platform. 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/ProAgentStore/platform/main/AGENTS.mdgit clone --depth 1 https://github.com/ProAgentStore/platformWrote 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/proagentstore/platform/agents-md)<a href="https://agentmods.dev/instructions/proagentstore/platform/agents-md"><img src="https://agentmods.dev/badge/instructions/proagentstore/platform/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/proagentstore/platform/agents-md"><img src="https://agentmods.dev/badge/instructions/proagentstore/platform/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 | $0.05231 | $0.05231 |
| Opus 5.5 | $0.02092 | $0.02092 |
| Sonnet 5.5 | $0.01046 | $0.01046 |
| Haiku 4.5 | $0.00523 | $0.00523 |
Grade A, and why
platform 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Delivery mode
Straight to main. No branches, no pull requests. Declared 2026-08-16.
No branches. No pull requests. Ever.
Commit directly to main. Do not run git checkout -b, git switch -c, or gh pr create. If you
find yourself on a non-main branch, stop and report it. (Declared 2026-08-16.)
Dev Workflow
- When completing development work in this repo, commit the finished change and push it to the tracked remote branch as part of the task. Do not leave completed dev work only in the local worktree unless the user explicitly asks not to commit or push.
- Project-local Codex agent specs live in
.codex/agents/. Keep the Dev Agent and BA Agent instructions there aligned with this workflow. - For tasks with two or more independent areas of investigation, use subagents in parallel. Delegate codebase exploration, documentation research, testing, and reviews where appropriate. Wait for relevant agents and consolidate their results before finishing.
Browser automation design (owner directive, 2026-11-04)
- Read
docs/browser-agent-design.mdbefore browser automation work. - AI interprets the live page, questions, controls and validation feedback. Do not fix a failed application by adding site-specific code, answer mappings, page-text regexes, CSS/HTML shape heuristics, or scripted form playbooks. Improve the model, its prompt, memory and available evidence first. Existing heuristics are technical debt, not precedent for adding more.
- Code may provide generic browser tools, screenshots, logging, configuration and execution integrity. Keep identity, source provenance, Stop, credential-origin and explicit submission authorization checks; do not remove them under the pretext of making the agent generic.
- Use current snapshots and, when needed and supported, screenshots as model input. Replay screenshots alone do not establish that the acting model can see images. Verify the tool path.
- Model choice belongs to each agent's execution configuration. Distinguish the cloud supervisor from the local browser-driving model. Do not claim a model switch from changing only the other model or adding prose. Verify the effective model from execution evidence.
- Escalation belongs to per-instance configuration, frozen per run. Let the acting model assess uncertainty and risk; code enforces the selected threshold without page-content heuristics. Delegated interpretation is not permission to invent missing personal facts or submit.
- Test reusable behavior on varied independent forms/components. A fix working on one employer page is not evidence of a generic solution. Report unsupported capabilities honestly.
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 Changed · +47 lines · +721 tokens per session 071c2bebc154
- 2d ago Changed · +19 lines · +306 tokens per session c4022d3b1140
- 11d ago Changed · +9 lines · +181 tokens per session b6c8a4a711c6
- 12d ago Changed · +24 lines · +451 tokens per session 6ade4ce4c9ae
- 21d ago Changed · +3 lines · +75 tokens per session 0fd07f15d2fa
- 24d ago Changed · +1 lines · +33 tokens per session b6fdb3870e01
- 25d ago Changed · +91 lines · +1,674 tokens per session 2503d64570f5
- 1mo ago Changed · +38 lines · +509 tokens per session 0ecf38150de8
- 1mo ago Changed · +8 lines · +133 tokens per session da182ae00093
- 2mo ago First seen · 101 lines · 1,148 tokens per session scan A aead649b3ce3
platform AGENTS.md is an instructions file published in the GitHub repository ProAgentStore/platform (1 stars, last pushed yesterday), licensed MIT. It adds 5,231 tokens to every session, about $0.0209 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.
platform AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| platform AGENTS.mdProAgentStore/platform | Instructions file | 1 | yesterday | MIT | A | 5,231 | 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 |