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 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/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/resume"><img src="https://agentmods.dev/badge/skills/aawwcc/ape/resume.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 | $0.00023 | $0.01027 |
| Opus 5.5 | $0.00009 | $0.00411 |
| Sonnet 5.5 | $0.00005 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00103 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
Pass the governed project root as project_dir on every APE MCP call. Inspect recovery_plan
and follow the returned action. Discovery preserves files and does not start workers:
-
confirm_recovery: review the exact source task, blocker, and runtime decision. Under this explicit resume invocation, callresumewith the returnedexpected_recovery_digestandexplicit_invocation: true. Keep any selectedlegacy_candidate_id,legacy_run_id, orrecovery_contextunchanged. Do not ask separately for a reset. The runtime chooses an eligible same-run gate retry, reconciles the existing shipment, or checkpoints and retires the blocked execution for fresh validation. A changed digest requires rediscovery; never reuse a stale plan. -
choose_recovery: show task objectives, source kinds, branches/stashes, dates, and blockers. Ask the user to select the source and associate it with a listed saved task (legacy_run_id), or supply its missing objective and scope inrecovery_context. Select only the returnedlegacy_candidate_id; rediscover with that selection before confirming its digest. Never apply or combine stashes yourself, guess task ownership from names, or import external backups. -
provide_recovery_context: obtain the missing objective, mode, lane, host, claimed paths and test paths for the selected source, then rediscover. The runtime records user-confirmed legacy provenance without inventing an earlier run or validation evidence. -
inspect_recovery: follow the concrete reason. Preserve unresolved workers/gates and newer edits. An intentional auto-merge hold remains held until an explicit ship request. Uncertain shipping must reconcile the existing pull request before creating a replacement execution. -
recover_checkpoint: the runtime found one available checkpoint. Callresumeagain with its exactcheckpoint_idandexplicit_invocation: true. -
choose_checkpoint: show the returned objectives, branches, and dates and ask which work to recover. Do not guess when several checkpoints exist or storage is incomplete/unreadable. -
start_recovered_work: files are restored on a new branch and reconciled with the locally resolved default branch. Read the saved failure reason as evidence, inspect what remains to be done, and address the original blocker. Use the returnedstart_inputas the basis of a fresh preview, keepingcheckpoint_idandsupersedes_run. Re-establish the current host, hooks, capabilities and runner configuration, review complete scope and admission, and perform the normal binding probe and start. If the response carriesstart_input_ref, read the complete saved input there and include the record'scheckpoint_idand, if present,source_run_idassupersedes_run. Start uses the restored recovery branch itself. Never reuse old tickets, receipts, permissions or test results.
An explicit resume invocation authorizes the returned blocked-run recovery, checkpoint restoration
and fresh validated run, including configured shipping, without another continuation approval.
explicit_invocation is the orchestrator's attestation, not authenticated human provenance.
It does not authorize overwriting newer work or choosing between different tasks.
On a recovery conflict or changed working files, preserve both versions and report the concrete
decision needed. If no active run or checkpoint exists, say so; never reconstruct files from memory.
Follow references/run-resume-protocol.md for dispatch,
receipt recording, waiting, and advancement, including redispatch_same_ticket and
capability_recovery. Use only the runtime-returned replacement or successor and follow its
frozen contract. Follow required_control_action before a generic continuation label:
recording an identical attested receipt does not require another worker validation.
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.
- 1mo ago Changed · +29 lines · +10 tokens per session 6a934866ac13
- 2mo ago Changed · +1 lines b2dcd4157080
- 2mo ago Changed · +2 lines 41d76fc3cd27
- 2mo ago Changed · +12 lines 17f771169426
- 2mo 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 24d ago), licensed MIT. It adds 23 tokens to every session and 1,027 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.
resume compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| resumeAAWWCC/ape | Skill | 0 | 24d ago | MIT | A | 23 | Claude Code |
| test-writingandreaswasita/copilot-agents-dojo | Skill | 55 | 2mo ago | MIT | A | 11 | Claude Code, Codex |
| tddSetraTheXX/Codex-Engineering-Workflow-Pack | Skill | 1 | 1mo ago | MIT | A | 43 | Claude Code, Codex |
| django-tddhashgraph-online/awesome-codex-plugins | Skill | 1.6k | today | Apache-2.0 | A | 32 | Claude Code, Codex |
| laravel-tddhashgraph-online/awesome-codex-plugins | Skill | 1.6k | today | Apache-2.0 | A | 27 | Claude Code, Codex |
| project-executionathola/claude-night-market | Skill | 350 | yesterday | MIT | A | 31 | Claude Code |
| iterative-developmentalinaqi/maggy | Skill | 711 | 1mo ago | MIT | A | 24 | Claude Code |