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 yimwoo/codex-agenteam --skill resumegit clone --depth 1 https://github.com/yimwoo/codex-agenteamWrote 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/yimwoo/codex-agenteam/resume)<a href="https://agentmods.dev/skills/yimwoo/codex-agenteam/resume"><img src="https://agentmods.dev/badge/skills/yimwoo/codex-agenteam/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/yimwoo/codex-agenteam/resume"><img src="https://agentmods.dev/badge/skills/yimwoo/codex-agenteam/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 | $0.00013 | $0.01707 |
| Opus 5 | $0.00006 | $0.00853 |
| Sonnet 5 | $0.00003 | $0.00341 |
| Haiku 4.5 | $0.00001 | $0.00171 |
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 9d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgenTeam Resume
Resume an interrupted pipeline run. Detects stale runs, verifies the last incomplete stage before continuing, and lets the user choose how to proceed.
Process
1. Detect Resumable Runs
python3 <runtime>/agenteam_rt.py resume-detect
Parse the JSON output:
-
No resumable runs (
resumable_runsis empty): Tell the user: "No interrupted runs found." Stop. -
One resumable run: Show summary: run_id, task, interrupted stage, last update time. Proceed to step 2.
-
Multiple resumable runs: List all with run_id, task, stage, and age (time since last_update). Ask the user which to resume. Proceed with their choice.
2. Get Resume Plan
python3 <runtime>/agenteam_rt.py resume-plan --run-id <run_id>
This returns a structured plan with all the information needed to decide how to resume: pipeline_mode, config drift status, interrupted stage details (verify, gate, baseline), completed and remaining stages.
3. Pipeline Mode Check
Read pipeline_mode from the resume plan:
-
standalone: Continue with the verify-first flow below (step 4+). -
hotl: This run was managed by HOTL's execution engine. Tell the user: "This is a HOTL-managed run. Resume with/hotl:resume <workflow-file>instead." Stop. AgenTeam does not resume HOTL-managed runs — HOTL owns the step-level state and verify-first logic for those runs. -
dispatch-only: Dispatch-only runs have no pipeline to resume. Tell the user: "Dispatch-only runs have no pipeline to resume. Re-assign tasks with@<Role> <task>." Stop.
4. Config Drift Check
If config_hash_match is false:
- Warn: "Config has changed since this run started (agenteam.yaml was modified). The run will use the original stage definitions from when it was created. Continue anyway? (yes/no)"
- If the user says no: stop.
- If yes: continue. Run-scoped commands use state snapshots, so config drift is safe — but the user should know.
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.
- 9d ago First seen · 197 lines · 13 tokens per session scan A 60137a6524d6
resume is a skill published in the GitHub repository yimwoo/codex-agenteam (13 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 1,707 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 2026-08-30.
Other skills, from other repositories
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.
lookup-topic
Look up a help topic with progressive depth. First call returns concept, repeat calls escalate to task then reference. Triggers on: look up topic, open template, tell me more, go deeper, start over.
lookup
Look up help topics with progressive depth. Pair with attune-ai for the full author-and-read workflow. Triggers on: lookup, look up, depth, topic, help topic, tell me more.