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/seakee/cpa-manager-plus/agents-mdgit clone --depth 1 https://github.com/seakee/CPA-Manager-PlusWrote 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/seakee/cpa-manager-plus/agents-md)<a href="https://agentmods.dev/instructions/seakee/cpa-manager-plus/agents-md"><img src="https://agentmods.dev/badge/instructions/seakee/cpa-manager-plus/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 | $0.01925 | $0.01925 |
| Opus 5 | $0.00962 | $0.00962 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
CPA-Manager-Plus 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Rules
For all agents. Shared approval semantics: /Users/seakee/.codex/prompt-policy.md; repo rules may only tighten them.
Operation
- Language: English unless the user asks otherwise.
- Dev flow: requirements -> read-only analysis -> plan -> explicit approval -> edit -> verify.
- Pre-approval: read files/history and run non-mutating commands only.
- Edit only user-named files or approved-plan files; dependent files may be read.
- Preserve unrelated user changes. No reset/checkout/delete/stage/commit/push/remote mutation without explicit approval.
- Prefer GitHub MCP
githubnamespace tools for GitHub-related operations: repository reads, refs, branches, tags, releases, issues, PRs, checks, commits, contents, and remote mutations. Examples includeget_me,pull_request_read,create_pull_request, andcreate_branch; legacy runtimes may expose the same tools asmcp__github__*. Use localgitfreely for local worktree and local history inspection. If the current session cannot actually call the required GitHub MCP tool, or if MCP cannot perform a required GitHub operation, state the MCP limitation and request explicit approval before using a scoped fallback such asgh,git fetch,git pull,git push,git ls-remote, or direct GitHub HTTP/API calls. - Local CPA source checkout:
/Users/seakee/WorkSpace/Golang/src/github.com/seakee/CPA. For CPA upstream code and history analysis, inspect this checkout first. Use GitHub MCP only when the required ref, issue/PR context, or remote metadata is unavailable locally. - Search with
rg/rg --files; manual edits withapply_patch. docs/plan/is a local ignored planning workspace. Use it for issue/epic plans, keepdocs/plan/roadmap.mdas the index, move near-term work toactive/, keep unscheduled work inbacklog/, and archive completed or superseded plans. Followdocs/plan/README.md.AGENTS.md/CLAUDE.mdare collaboration files; commit them only on explicit request.
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.
- 3d ago First seen · 126 lines · 1,925 tokens per session scan A 8d893e6c9230
CPA-Manager-Plus AGENTS.md is an instructions file published in the GitHub repository seakee/CPA-Manager-Plus (3,033 stars, last pushed yesterday), licensed MIT. It adds 1,925 tokens to every session, about $0.0096 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
recondo CLAUDE.md
Instructions for recondodev/recondo, covering recondo, build & run, test the gateway, automated tests (678 tests, 5 seconds) and test suite map.
recondo AGENTS.md
Instructions for recondodev/recondo, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
OmniRoute CLAUDE.md
Claude Code instructions for diegosouzapw/OmniRoute, covering claude.md, worktree isolation — claude code specifics, cross-session safety — claude code specifics, superpowers / planning artifacts — path overrides and scratch / temporary files — use artifacts/, not /tmp.
opensre AGENTS.md
AGENTS.md instructions for Tracer-Cloud/opensre, covering opensre development reference, ci failures and tests (mandatory — every pr / push), build and run commands, code style and tests (high-signal, not exhaustive).
openlit AGENTS.md
AGENTS.md instructions for openlit/openlit, covering openlit agent rules, ce/oss boundary, extension points, project hierarchy and ui and security.
evlog AGENTS.md
AGENTS.md instructions for HugoRCD/evlog, covering evlog, commands, monorepo structure, conventions and code style: no slop.