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/tk-wxy/apc.md/agents-mdgit clone --depth 1 https://github.com/tk-wxy/apc.mdWrote 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/tk-wxy/apc.md/agents-md)<a href="https://agentmods.dev/instructions/tk-wxy/apc.md/agents-md"><img src="https://agentmods.dev/badge/instructions/tk-wxy/apc.md/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 | $0.00315 | $0.00315 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
apc.md 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 4d 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
Agent Entry
Read .apc/manifest.md first. .apc/workflow.md is the
development-protocol source of truth.
Route
Choose one route:
- Initialize a consumer project
- Condition: the manifest contains
{{...}}and the user requests initialization. - Follow
.apc/init.md; it overrides normal startup.
- Condition: the manifest contains
- Maintain APC itself
- Condition: placeholders and bundled APC docs/examples remain, and the task explicitly concerns this framework.
- Treat
.apc/as distributable prompt source. - You may edit boilerplate, but never fill placeholders or record framework state in consumer manifest, memory, rules, or decisions.
- Work in an initialized project
- Follow
.apc/workflow.md§0 on first contact, otherwise §1.
- Follow
- Ambiguous uninitialized project
- For ordinary product work with placeholders still present, stop and ask the user to initialize APC.
If a route's required file is unreadable, stop and report its path.
Task end
Before the final summary, follow .apc/workflow.md §4. Persist only
material, verified knowledge or state. A no-op is valid.
Core
- Diagnose before modifying.
- Inspect before asking; ask only about material ambiguity.
- Change one variable at a time in high-risk areas.
- Repeated failure at one point means stop and reassess.
- Stay consistent with the manifest.
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.
- 4d ago First seen · 40 lines · 315 tokens per session scan A a41d1c00bf59
apc.md AGENTS.md is an instructions file published in the GitHub repository tk-wxy/apc.md (2 stars, last pushed 26d ago), licensed MIT. It adds 315 tokens to every session, about $0.0016 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 2026-08-31.
Other instructions, from other repositories
agent-starter-kit AGENTS.md
Instructions for ntorga/agent-starter-kit, covering agents.md, honesty and ambiguity, code shape, function extraction and duplication.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.
agent-skills AGENTS.md
AGENTS.md instructions for simota/agent-skills, covering agents.md — claude-skills, repository purpose, language policy, repository structure and skill authoring conventions.
gemini-kit GEMINI.md
Instructions for nth5693/gemini-kit, covering gemini-kit: super engineer team, role & responsibilities, workflows, team members and workflow.
hermes-model-auto-switch AGENTS.md
Instructions for rhishi99/hermes-model-auto-switch, covering install, verify, uninstall, guardrails and conventions.
agy-plugin-cc CLAUDE.md
Instructions for Vit129/agy-plugin-cc, covering agy-plugin-cc — claude code guide, agent memory, global-first rule, project context (auto-loaded every session) and project summary.