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 skills add AAWWCC/ape --skill configgit clone --depth 1 https://github.com/AAWWCC/apeWrote 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/skills/aawwcc/ape/config)<a href="https://agentmods.dev/skills/aawwcc/ape/config"><img src="https://agentmods.dev/badge/skills/aawwcc/ape/config/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/skills/aawwcc/ape/config"><img src="https://agentmods.dev/badge/skills/aawwcc/ape/config.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 | $0.00018 | $0.00425 |
| Opus 5.5 | $0.00007 | $0.00170 |
| Sonnet 5.5 | $0.00004 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
config 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 1mo 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
APE config
Use only when the user explicitly requests APE configuration work. Pass the governed project root
as project_dir; apply only changes covered by the user's instruction. Call ape_config with:
get: read configuration, optionally at a dot-path key.set: write the requested dot-path value. Preserve unrelated sparse overrides.doctor: diagnose runtime, git, hook, bundle, lock, and statusline readiness. Supply run-start facts only when validating a prospective run.init: inspect manifests, or exact prospectivebehavioral/test_pathsfor a blank repository, and propose commands without writing. Useapply: trueonly within existing explicit approval; user-suppliedvaluesoverride proposed slots. An explicit run authorizes filling missing required slots from a complete grounded proposal. Compare withget; preserve existing values, using scopedsetcalls if applying the proposal would overwrite them. Enrollevidence_scriptsonly when the user explicitly accepts those exact discovered script IDs.initdoes not create or edit repository instruction files such asAGENTS.md,AGENTS.override.md, orCLAUDE.md. Those files are optional and repository-owned; the runtime injects its operational orientation at session start.wire/unwire: change statusline integration for an explicitly named host.
Do not translate host-neutral test commands into platform-specific shell strings. Do not claim the Codex native status line is the custom APE renderer. State the exact key, values, or host being changed without asking again for approved work. Ask only for missing choices or changes outside that approval; report tool warnings and rejected fields without weakening them.
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.
- 1mo ago Changed d91a96ae3b89
- 2mo ago Changed · +2 lines 101f8cae3dbf
- 2mo ago First seen · 30 lines · 18 tokens per session scan A 2ff167c031dd
config is a skill published in the GitHub repository AAWWCC/ape (0 stars, last pushed 24d ago), licensed MIT. It adds 18 tokens to every session and 425 once invoked, about $0.0001 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.
config compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| configAAWWCC/ape | Skill | 0 | 24d ago | MIT | A | 18 | Claude Code |
| refactorirahardianto/awesome-agv | Skill | 161 | 1mo ago | MIT | A | 38 | Claude Code |
| bugfixirahardianto/awesome-agv | Skill | 161 | 1mo ago | MIT | A | 44 | Claude Code |
| icodeayukyo/icode-skill | Skill | 6 | today | MIT | A | 193 | Codex |
| fix-issuejoris887/exosuit | Skill | 9 | 13d ago | MIT | A | 27 | Claude Code |
| debuggingandreaswasita/copilot-agents-dojo | Skill | 55 | 2mo ago | MIT | A | 13 | Claude Code, Codex |
| test-writingandreaswasita/copilot-agents-dojo | Skill | 55 | 2mo ago | MIT | A | 11 | Claude Code, Codex |