Borrowing it
Nothing to install: this file belongs to runxhq/runx. 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/runxhq/runx/main/AGENTS.mdgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/agents-md)<a href="https://agentmods.dev/instructions/runxhq/runx/agents-md"><img src="https://agentmods.dev/badge/instructions/runxhq/runx/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/runxhq/runx/agents-md"><img src="https://agentmods.dev/badge/instructions/runxhq/runx/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 | $0.03019 | $0.03019 |
| Opus 5.5 | $0.01208 | $0.01208 |
| Sonnet 5.5 | $0.00604 | $0.00604 |
| Haiku 4.5 | $0.00302 | $0.00302 |
Grade A, and why
runx 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scafld Agent Contract
Default Agent Flow
Work with the host agent's normal planning, editing, and testing tools. When the work appears done, call review, then call finalize.
review is the independent provider gate. It records accepted review evidence and returns blockers or a passing review. finalize consumes that accepted review, records deterministic acceptance evidence, signs the receipt, and archives the spec. It never invokes a provider or model. The agent does not grade its own completion.
The receipt reports its independence level honestly. cross_vendor means multi-model review that can reduce correlated blind spots; it is still single-party local tooling unless a separate operator or CI trust domain verifies the receipt. isolation_only means the reviewer was isolated but cross-vendor separation was not proven.
Merge Wall
CI runs scafld verify <receipt> --target <commit-ish> against the signed receipt. This is the hard wall for merging. The Claude Stop hook is only a local affordance; it can be bypassed in subagents, piped runs, Codex, Gemini, or other hosts.
Human And CI Lifecycle
The full CLI lifecycle remains available for operators, automation, and debugging:
scafld init
scafld plan <task-id> --title "Title" --size small --risk low
scafld harden <task-id>
scafld validate <task-id>
scafld approve <task-id>
scafld build <task-id>
scafld review <task-id>
scafld finalize <task-id>
scafld verify <receipt> --target <commit-ish>
scafld status <task-id>
scafld handoff <task-id>
Use scafld harden to strengthen drafts before approval. Use scafld build to record phase evidence. Use scafld review for the provider gate, then scafld finalize after a passing review. scafld complete is a legacy ledger transition and is not required after finalize. Use scafld status --json for automation.
For manual acceptance, use scafld build <task-id> --criterion <id> --disposition pass --evidence-digest <sha256> --actor <actor> --reason <what-was-verified>. Never edit criterion state or substitute a fake shell check.
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 · +5 lines · +54 tokens per session 608804a689f9
- 20d ago Changed · +8 lines · +107 tokens per session baea50ba021d
- 22d ago Changed · +2 tokens per session 9e29d2bf3da8
- 24d ago Changed · +3 tokens per session 9b22d6889f3e
- 26d ago Changed b785a14a7173
- 1mo ago Changed · -71 lines · -356 tokens per session 8be971fd6c5d
- 2mo ago First seen · 359 lines · 3,209 tokens per session scan A ce4667d2890c
runx AGENTS.md is an instructions file published in the GitHub repository runxhq/runx (104 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,019 tokens to every session, about $0.0121 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.
runx AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| runx AGENTS.mdrunxhq/runx | Instructions file | 104 | yesterday | Apache-2.0 | A | 3,019 | 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 | 5,516 | GitHub Copilot |
| 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 |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |