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 OutlineDriven/outline-driven-development --skill enforce-workflow-constraintsgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/enforce-workflow-constraints)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/enforce-workflow-constraints"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/enforce-workflow-constraints/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/outlinedriven/outline-driven-development/enforce-workflow-constraints"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/enforce-workflow-constraints.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00885 |
| Opus 5 | $0.00028 | $0.00443 |
| Sonnet 5 | $0.00011 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
enforce-workflow-constraints 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- enforce-workflow-constraints — 100% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enforce workflow constraints
Contract
| Field | Bound contract |
|---|---|
| Trigger | Any bounded workflow starts, or reaches an action, path, proposal, or merge boundary |
| Authority | Read-only; no file, VCS, credential, paid, published, deployed, or remote mutation. Permits, narrows, or refuses the pending action in chat output and records the refusal reason; never proceeds on an unread constraint set |
| Side effect | Chat output only; permits, narrows, or refuses the pending action and records the refusal reason. Never mutates files, state, or remote targets |
| Done | Constraints were loaded before the first action and re-evaluated at every boundary; an unreadable constraint set produced refusal, not default-allow |
Inputs
- The constraint set that bounds the workflow. It must be supplied or locatable before the first action. If it is unreadable, missing, or too ambiguous to enforce, refuse the workflow.
- The pending action, path, proposal, or merge at each boundary. It must be supplied at evaluation time.
- Optional: the prior verdict sequence for continuity across boundaries within the same workflow.
Procedure
- Before the first action of any bounded workflow, load the constraint set that bounds it. If the constraint set is unreadable, missing, or ambiguous to the point of being unenforceable, refuse the workflow and record the refusal reason. Do not default-allow. Done when: the constraint set is loaded and enforceable, or the workflow is refused with a recorded reason.
- At every action boundary, re-evaluate the loaded constraints against the pending action. Permit the action if it satisfies every constraint; narrow it to a compliant form if a narrower action would satisfy them; refuse it and record the refusal reason if no compliant form exists. Done when: the pending action is permitted, narrowed, or refused with a recorded verdict.
- At every path boundary, re-evaluate the constraints against the chosen execution path. Permit, narrow, or refuse as in step 2. Done when: the chosen path is permitted, narrowed, or refused with a recorded verdict.
- At every proposal boundary, re-evaluate the constraints against the proposed change. Permit, narrow, or refuse as in step 2. Done when: the proposed change is permitted, narrowed, or refused with a recorded verdict.
- At every merge boundary, re-evaluate the constraints against the merge target and content. Permit, narrow, or refuse as in step 2. Done when: the merge target and content are permitted, narrowed, or refused with a recorded verdict.
- Record every refusal with its reason in chat output. If the constraint set may have changed since the last load, reload it before re-evaluating; never proceed on a stale or unread constraint set. Done when: every refusal is recorded with its reason and no stale constraint set was used.
What ships with it
1 file 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.
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.
- 5d ago First seen · 41 lines · 56 tokens per session scan A f18b461b3193
enforce-workflow-constraints is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 56 tokens to every session and 885 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.