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 nirecom/agents --skill enforce-workflow-offgit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/enforce-workflow-off)<a href="https://agentmods.dev/skills/nirecom/agents/enforce-workflow-off"><img src="https://agentmods.dev/badge/skills/nirecom/agents/enforce-workflow-off/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/nirecom/agents/enforce-workflow-off"><img src="https://agentmods.dev/badge/skills/nirecom/agents/enforce-workflow-off.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 | $0.00024 | $0.01043 |
| Opus 5.5 | $0.00010 | $0.00417 |
| Sonnet 5.5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
enforce-workflow-off 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 today.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The session-scoped escape hatch. Use only as a last resort, for the cases rules/workflow-off.md names; that rule owns the trigger, this skill owns the procedure.
When the user invoked this skill
Generate a 1-line reason from the current context describing the intended action, then run:
echo "<<WORKFLOW_ENFORCE_WORKFLOW_OFF_EMERGENCY: [{category}] {reason}>>"
Explicit user invocation IS the human decision — it carries the same trust as the EMERGENCY escape hatch, so the Phase1 clearance examination is deliberately bypassed here (#1780).
The "ask" permission still fires a user confirmation dialog; the activation is still recorded in the supervisor audit trail as an escape_hatch_event.
Never emit this sentinel on your own initiative — only when the user invoked this skill.
Provenance is recorded independently of this instruction: typing /enforce-workflow-off stamps the audit record provenance=user_skill_invocation for either target this skill covers, any other route — and any invocation record that cannot be verified and consumed — stamps provenance=unattributed (which means "not provably user-invoked", not "misused").
Use bash "$AGENTS_MAIN_ROOT/bin/request-off-mode-clearance" instead when YOU (not the user) need an OFF departure; it mints the clearance the non-emergency sentinel below requires.
Sentinels
| Command | Permission | Effect |
|---|---|---|
the clearance-gated standard WORKFLOW_ENFORCE_WORKFLOW_OFF form — never emitted by this skill; see rules/workflow-off.md |
ask | Creates ${sid}.workflow-off; suspends workflow enforcement (and, subsumed, worktree enforcement) |
echo "<<WORKFLOW_ENFORCE_WORKFLOW_OFF_EMERGENCY: [{category}] {reason}>>" |
ask | Same marker, but bypasses the Phase1 clearance examination |
echo "<<WORKFLOW_ENFORCE_WORKFLOW_ON: {reason}>>" |
allow (auto-approved) | Removes the marker; restores enforcement |
echo "<<WORKFLOW_ENFORCE_WORKTREE_OFF: {reason}>>" |
ask | Creates ${sid}.worktree-off; lifts only enforce-worktree.js |
echo "<<WORKFLOW_ENFORCE_WORKTREE_ON: {reason}>>" |
allow (auto-approved) | Removes that marker; worktree enforcement restored |
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.
- today Changed 277c8dcd9d1f
- 11d ago Changed 635d5ea21f3f
- 17d ago Changed 96d1893bac83
- 1mo ago Changed d35b4ca18289
- 1mo ago First seen · 54 lines · 24 tokens per session scan A e0597ade3c9a
enforce-workflow-off is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,043 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…