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 skills/aawwcc/ape/resumenpx skills add AAWWCC/ape --skill resumegit 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/resume)<a href="https://agentmods.dev/skills/aawwcc/ape/resume"><img src="https://agentmods.dev/badge/skills/aawwcc/ape/resume.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 | $0.00013 | $0.00470 |
| Opus 5 | $0.00006 | $0.00235 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
resume 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 today.
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 resume
Use only when the user explicitly asks to resume APE. Call ape_run with action: "resume" and
continue from the returned machine state; never reconstruct completed work or pending tickets from
conversation memory.
On Google Antigravity / Gemini, pass the exact open project root as project_dir on every APE MCP
call.
Follow references/run-resume-protocol.md for dispatch,
receipt recording, waiting, and advancement. Never spawn a replacement for an already-bound ticket
unless the runtime returns next_action: {"kind":"redispatch_same_ticket", ...}; that action authorizes at most
one fresh worker on the same immutable ticket after receipt-contract correction exhaustion.
When the runtime instead returns next_action.kind: "capability_recovery", dispatch only the
included runtime-derived successor. It consumes no product attempt and already binds the exact
additive scope, policy, deadlines, manifests, run contract, lineage ceilings, and provenance. Never
mint or alter a successor. If the response was lost, record the identical source receipt again; the
runtime validates and adopts the same complete immutable generation rather than charging another
successor. Canonical test-path unions are limited to 64 items and 4096 serialized UTF-8 JSON bytes,
and the lineage remains bounded to three validation submissions per worker and two workers per
ticket.
The resume invocation authorizes continuous scheduler-owned progress. Drive every returned
transition, wait, review, replan, remediation, gate, and configured shipping action to a terminal
result without asking the user to say continue. Yield only for completion, a terminal block, or
input that would change the requested outcome.
When a dispatch remains active, wait through the host's native agent primitive. Use
expire-dispatch only for a genuinely orphaned or wedged flight, with the exact pending ticket ID
and a non-empty user-provided audit reason.
Accept the runtime's current lane, model policy, retry count, remediation state, and gate state. Do not redo stages, free-hand transitions, or edit files from the parent session.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +12 lines 17f771169426
- 4d ago First seen · 25 lines · 13 tokens per session scan A e431aaa3d5d3
resume is a skill published in the GitHub repository AAWWCC/ape (0 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 470 once invoked, about $0.0001 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 skills, from other repositories
agent-orchestrator-v2
Agent Orchestrator workflow skill. Use this skill when the user needs Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management and the operator should preserve the upstream workflow, copied support files, and…
self-improvement
Captures lessons and promotes recurring patterns.
brainstorming
Refines rough ideas into approved designs before code.
code-review
Reviews diffs by severity to produce actionable feedback.
codebase-onboarding
Maps an unfamiliar repo before touching its code.
debugging
Systematic root-cause investigation for hard bugs.