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 eugenelim/agent-ready-repo --skill work-loopgit clone --depth 1 https://github.com/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/work-loop)<a href="https://agentmods.dev/skills/eugenelim/agent-ready-repo/work-loop"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/work-loop.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 34 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 50 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 109 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 219 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- high Rogue Agent · line 370 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00161 | $0.16280 |
| Opus 5 | $0.00081 | $0.08140 |
| Sonnet 5 | $0.00032 | $0.03256 |
| Haiku 4.5 | $0.00016 | $0.01628 |
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 — 814 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: work-loop
Work-loop contract
Surface = stop the current loop, emit a brief description of the situation (what happened, what you tried, current state), name the minimum viable recovery rung, and wait for human direction. Do not retry, redispatch, or silently continue. Recovery rungs in cost order: steer (redirect this session with corrected instructions — cheapest; preserves context) / rerun (new session, gap-closed brief — keeps prior commits, discards context) / salvage (manual recovery from the last clean branch — use when agent state is irrecoverable). (Reviewers also "surface" findings in the descriptive sense — context disambiguates.)
State flow: PLAN → EXECUTE → GATES → REVIEW → DECIDE. After a fix, return to GATES.
┌─────────────────────────────────────────────────────────┐
│ │
▼ │
PLAN ──► EXECUTE ──► GATES ──► REVIEW ──► DECIDE │
│ │ │ │
└─ failed? ─┴── findings? ──── fix ┘
└── back to GATES
Self-coverage gate. Between human gates, resolve everything a referent can resolve; surface only the irreducible. Three net-new obligations per loop: (1) conditional domain-grounding at PLAN (only when the build rests on an ungrounded domain claim); (2) resolve-vs-surface disposition record, opened at PLAN and closed at DECIDE; (3) done-checklist refusal — don't declare done until the record exists and every REVIEW finding is resolved. The obligations above are the operative runtime contract. Use references/self-coverage/resolve-vs-surface.md only when a disposition is ambiguous; references/self-coverage/protocol.md contains design rationale and calibration, not required normal-loop instructions.
What ships with it
35 files 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.
- assets/state.json 890 B
- evals/evals.json 62 KB
- evals/files/cognitive-load/ordinary-prose.md 215 B
- evals/files/cognitive-load/quiet-exceptions.json 531 B
- evals/files/cognitive-load/quiet-routine.json 200 B
- references/delivery-contract-lifecycle.md 6.7 KB
- references/finding-adjudication.md 15 KB
- references/infra-verification.md 18 KB
- references/light-mode.md 8.1 KB
- references/policy-families.md 5.5 KB
- references/pre-execute-review.md 15 KB
- references/pre-flight-failures.md 5.0 KB
- references/review-verdict-record.md 6.8 KB
- references/scale-with-a-tool.md 9.3 KB
- references/self-coverage/protocol.md 2.3 KB
- references/self-coverage/resolve-vs-surface.md 5.0 KB
- references/session-resumption.md 7.7 KB
- references/state-schema.md 16 KB
- references/supervisor-mode.md 13 KB
- references/tdd-stubs.md 14 KB
- references/unattended-loops.md 617 B
- references/verification-modes.md 4.6 KB
- scripts/_loop_guards.py 62 KB runs code
- scripts/_statelock.py 16 KB runs code
- scripts/append-knowledge.py 1.2 KB runs code
- scripts/check-base-freshness.py 20 KB runs code
- scripts/check-spec-status.py 7.6 KB runs code
- scripts/file_safety.py 19 KB runs code
- scripts/lint-knowledge.py 23 KB runs code
- scripts/lint-spec-status.py 57 KB runs code
- scripts/lint-traceability.py 61 KB runs code
- scripts/loop-cohort.py 111 KB runs code
- scripts/loop-engine.py 66 KB runs code
- scripts/review-artifact.py 10 KB runs code
- scripts/select-policy-families.py 12 KB runs code
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 Changed · -23 lines ea887efd7e9f
- 3d ago Changed · +4 lines 941977a4bd98
- 4d ago Changed · -128 lines 90793da90b46
- 7d ago First seen · 961 lines · 161 tokens per session scan A 8da8941164d1
work-loop is a skill published in the GitHub repository eugenelim/agent-ready-repo (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 161 tokens to every session and 16,280 once invoked, about $0.0008 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
supervisor
Autonomous multi-agent quality supervisor and release gate. Use when a user wants the best possible result, asks for rigorous review, or when a substantive answer/deliverable should be challenged before release. Decomposes the task, fans out independent subagents, uses specialist and adversarial judges, verifies…
moai-platform-chrome-extension
Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.
moai-framework-electron
Electron 33+ desktop app development specialist covering Main/Renderer process architecture, IPC communication, auto-update, and packaging with Electron Forge. Use when building cross-platform desktop applications.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
moai-platform-database-cloud
Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases.
review-claudemd
Review recent conversations to find improvements for CLAUDE.md files.