Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/pax-beehive/paxm/agents-mdgit clone --depth 1 https://github.com/pax-beehive/paxmWrote 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/pax-beehive/paxm/agents-md)<a href="https://agentmods.dev/instructions/pax-beehive/paxm/agents-md"><img src="https://agentmods.dev/badge/instructions/pax-beehive/paxm/agents-md.svg" alt="Measured on agentmods" 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 | $0.00552 | $0.00552 |
| Opus 5 | $0.00276 | $0.00276 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
paxm 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 6d 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.
What it actually says
paxm 开发要求
Git 与协作
main受保护，禁止直接开发、强推或删除；每项工作从最新main创建codex/<topic>分支，提交 PR，等待 CI 与至少一次 review 后合入。- PR 只包含任务相关改动；勿覆盖或提交他人的未提交文件。
- 提交小而可解释；不要顺手 release、改配置或上传私密数据。
架构边界
- CLI 只负责参数解析和输出；运行时通过 facade/tools、memory router、provider adapter 分层调用。不要让 CLI 直接依赖具体 provider。
- setup、配置、安装、日志/观测属于 operator；recall/remember 等 agent-facing tools 保持窄接口；provider 新增走现有 registry/config/adapter seam。
- 用户负责 key、hook 信任和安装；agent 只调用明确的 recall/write 能力。被动 hook 必须 fail-open，不能阻塞 agent。
- 新 agent 集成必须验证真实 runtime 的被动写入、全新会话召回、MCP 召回、 session/workspace/event 顺序，并提供禁用、升级和回滚路径。
代码与验证
- 使用 Go 1.25；改 Go 文件后运行
gofmt。生产逻辑要清晰拆分，避免为拆而拆。 - 提交前至少运行：
go test ./... -count=1、go vet ./...、golangci-lint fmt --diff、golangci-lint run。 - 复杂度门禁：
scripts/check-production-complexity.sh，圈复杂度 <=20、 认知复杂度 <=25。覆盖率门禁：go test ./... -covermode=atomic -coverprofile=coverage.out后运行scripts/check-production-coverage.sh coverage.out 75；产品代码覆盖率必须 >=75%。 - 变更行为就补单元/集成测试。eval、bench、conformance 不替代单元测试；付费的 cross-agent eval 只显式运行，不放入 CI。
文档与发布
- 行为、配置、架构或路线变化同步更新
README.md、docs/。 - 发布遵循
docs/release.md：先 PR/CI，再合入、打 tag 和发布；不要把发布动作 混入普通开发 PR。
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.
- 6d ago First seen · 39 lines · 552 tokens per session scan A 4845e677b1b2
paxm AGENTS.md is an instructions file published in the GitHub repository pax-beehive/paxm (421 stars, last pushed 8d ago), licensed Apache-2.0. It adds 552 tokens to every session, about $0.0028 per session on Opus 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.
Other instructions, from other repositories
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
personal-model CLAUDE.md
Instructions for Intuition-Lab/personal-model: Read and follow AGENTS.md. It is the single agent orientation for this repository: Runtime boundary, commands, architecture, invariants, current documentation, privacy rules, and DCO workflow.
brigade AGENTS.md
AGENTS.md instructions for escoffier-labs/brigade, covering agents.md, definition of done, rules, orientation and memory handoff.
engraphis CLAUDE.md
Claude Code instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.