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/abilityai/abilities/work-loopnpx skills add Abilityai/abilities --skill work-loopgit clone --depth 1 https://github.com/Abilityai/abilitiesWhat 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 | $0.00031 | $0.01409 |
| Opus 5 | $0.00015 | $0.00705 |
| Sonnet 5 | $0.00006 | $0.00282 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
work-loop 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 2d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Loop
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.work-loop vX.Y — recent: <summary>. Then proceed.
Autonomous skill that picks one issue from the backlog, executes it, and exits. The scheduler re-invokes it for the next issue — one issue per context window.
Purpose
Run on a schedule (or manually) to autonomously advance the agent's task backlog. Each invocation handles exactly one issue, keeping context focused and noise-free. The cron handles iteration; this skill handles execution.
State Dependencies
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| GitHub Issues | Current repo | Yes | Yes | Task backlog |
| GitHub Labels | status:, priority:, skill:* | Yes | Yes | Track status and route by skill |
| Agent Skills | .claude/skills/ | Yes | No | Available capabilities |
| CLAUDE.md | ./CLAUDE.md | Yes | No | Agent identity and guidelines |
Prerequisites
ghCLI authenticated- Repository has required labels (status:todo, status:in-progress, priority:*)
- Agent has skills to handle the types of issues in backlog
Process
Step 1: Check for In-Progress Work
gh issue list --label "status:in-progress" --state open --json number,title,body,labels --limit 1
If an issue is in-progress:
- This is the current task
- Parse the issue body for requirements
- Continue working on it (skip to Step 3)
If no in-progress work, proceed to Step 2.
Step 2: Pick Next Task
Find highest priority todo:
# P0 first
gh issue list --label "priority:p0" --label "status:todo" --state open --json number,title,body,labels --limit 1
# Then P1
gh issue list --label "priority:p1" --label "status:todo" --state open --json number,title,body,labels --limit 1
# Then P2
gh issue list --label "priority:p2" --label "status:todo" --state open --json number,title,body,labels --limit 1
# Then any todo
gh issue list --label "status:todo" --state open --json number,title,body,labels --limit 1
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.
- 2d ago First seen · 165 lines · 31 tokens per session scan A ae01d3ff21e1
work-loop is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 31 tokens to every session and 1,409 once invoked, about $0.0002 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
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.