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/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/eugenelim/agent-ready-repo/work-loop"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/work-loop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.16953 |
| Opus 5.5 | $0.00064 | $0.06781 |
| Sonnet 5.5 | $0.00032 | $0.03391 |
| Haiku 4.5 | $0.00016 | $0.01695 |
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 — 875 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. Work frontier. Resolve findings required to satisfy current intent. Do not expand the work frontier unless the finding blocks correctness, security, or the stated acceptance criteria. The two rules compose in that order: the frontier rule decides whether a finding is in scope, and only then does the self-coverage rule decide whether to resolve it against a referent or Surface it. A finding outside the frontier is resolved, not Surfaced, and its referent is the accepted intent: the intent does not require it, so DECIDE excludes it. That is a resolution, never a third disposition, so the resolve-vs-surface seam is unchanged. 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
60 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/pull-request-template.md 1.5 KB
- assets/state.json 919 B
- evals/evals.json 135 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
- profiles/work-loop.toml 1.5 KB
- references/bundled-fixes.md 3.9 KB
- references/capture.md 5.2 KB
- references/delivery-contract-lifecycle.md 8.9 KB
- references/finding-adjudication.md 15 KB
- references/full-mode-engine.md 13 KB
- references/infra-verification.md 18 KB
- references/knowledge-base.md 1.7 KB
- references/light-mode.md 8.2 KB
- references/model-selection.md 1.4 KB
- references/mutation-proof.md 2.3 KB
- references/policy-families.md 6.6 KB
- references/pr-authoring.md 3.8 KB
- references/pre-execute-review.md 15 KB
- references/pre-flight-failures.md 5.0 KB
- references/review-verdict-record.md 7.6 KB
- references/reviewer-roster.md 2.8 KB
- references/scale-with-a-tool.md 9.4 KB
- references/self-coverage/protocol.md 2.3 KB
- references/self-coverage/resolve-vs-surface.md 4.8 KB
- references/session-resumption.md 8.3 KB
- references/skill-engineering-provider.md 3.6 KB
- references/state-schema.md 24 KB
- references/supervisor-mode.md 22 KB
- references/tdd-stubs.md 15 KB
- references/unattended-loops.md 617 B
- references/verification-modes.md 4.6 KB
- references/work-item-capture.md 9.1 KB
- review-rules.json 5.2 KB
- scripts/_acceptance.py 20 KB runs code
- scripts/_compat_facade.py 34 KB runs code
- scripts/_confined_mutation.py 23 KB runs code
- scripts/_containment.py 34 KB runs code
- scripts/_content_safety.py 18 KB runs code
- scripts/_delivery_feed.py 18 KB runs code
- scripts/_effect_broker.py 15 KB runs code
- scripts/_evidence_store.py 171 KB runs code
- scripts/_file_safety.py 19 KB runs code
- scripts/_knowledge_projection.py 13 KB runs code
- scripts/_loop_guards.py 92 KB runs code
- scripts/_policy_import.py 43 KB runs code
- scripts/_process_safety.py 78 KB runs code
- scripts/_review_assessment.py 17 KB runs code
- scripts/_review_bridge.py 9.6 KB runs code
- scripts/_review_compat.py 29 KB runs code
- scripts/_review_contracts.py 24 KB runs code
- scripts/_review_disposition.py 15 KB runs code
- scripts/_review_persistence.py 5.1 KB runs code
- scripts/_review_selection.py 20 KB runs code
- scripts/_security_capability.py 20 KB runs code
- scripts/_security_events.py 15 KB runs code
- scripts/_statelock.py 17 KB runs code
- scripts/_subject_projection.py 8.3 KB runs code
- scripts/_subject_source.py 25 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 cbb450936aaa
- 3d ago Changed · +1 lines 7bfd6a52c258
- 11d ago Changed abd1f25e47b2
- 14d ago Changed 425e7744077b
- 14d ago Changed e70682aa180c
- 22d ago Changed · +4 lines e1557a23bec7
- 24d ago Changed 986ac805e262
- 27d ago Changed · +2 lines 620fd715cf56
- 28d ago Changed · +1 lines 91cd16dd0dea
- 1mo ago First seen · 867 lines · 161 tokens per session scan A 85bc457b9b76
work-loop is a skill published in the GitHub repository eugenelim/agent-ready-repo (26 stars, last pushed today), licensed Apache-2.0. It adds 161 tokens to every session and 16,953 once invoked, about $0.0006 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 2026-08-30.
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-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.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
verify
Answer "is this shippable / done?" with evidence before a commit or PR — fires on "verify", "is this done", "ready to ship?", pre-commit or pre-PR. Part of the Agentsmith harness; runs the project's verify phases and never claims "passing" without showing the output (R5).
api-baas-neon
Serverless PostgreSQL with branching, autoscaling, and edge-compatible driver.