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 clean-and-truegit 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/clean-and-true)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/clean-and-true"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/clean-and-true/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/clean-and-true"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/clean-and-true.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 | $0.00045 | $0.00754 |
| Opus 5 | $0.00023 | $0.00377 |
| Sonnet 5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
clean-and-true 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean and true
Contract
| Field | Bound contract |
|---|---|
| Trigger | Fires automatically after editing a durable artifact, or when the user says "clean and true", "run the hygiene pass", or "taste your own output". |
| Authority | Reversible local: writes only the just-changed durable artifact; rollback is restoring that artifact's prior on-disk content. No VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | May revise the just-changed local artifact through applicable hygiene passes only. |
| Done | Every applicable hygiene route ran or has a stated skip reason; findings are applied or explicitly deferred; no-op when nothing improves. |
Inputs
- The just-changed durable artifact (path or content). Must be supplied.
- The set of hygiene passes available in the session. Optional; a pass absent from the session is skipped with a stated reason.
Procedure
-
Identify the just-changed durable artifact and bound scope to it; do not read or edit any other file. Done when: the artifact is identified and scope is bounded to it.
-
Classify what changed in the artifact and route to the hygiene pass the change earned:
What changed Hygiene route Skip when Drifted prose that reads as sediment Rewrite as a clean v0 from current truth No sediment accumulated Padded prose whose every rule still binds Debloat: cut what no rule depends on Nothing padded to cut Anything a stranger must understand alone Cold-read for standalone clarity Short-lived or author-only A reality-grounded claim Verify the claim both ways No such claim present A truth duplicated across places SSOTize: fold into one home, point the rest at it A single home already holds it Voice, tells, or stack residue in prose Strip tells and restore voice Not prose, or not stale Done when: each change is classified and routed to its hygiene pass or marked with a skip reason.
-
Run each routed pass over the artifact. Skip any pass not available in the session with a stated reason. Done when: every routed pass is run or skipped with a reason.
-
Apply the findings to the artifact in this session. Done when: findings are applied to the artifact or explicitly deferred with a reason.
-
If a pass finds no genuine improvement, leave the artifact unchanged for that route. Done when: each route is confirmed as applied, deferred, or no-op.
What ships with it
2 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.
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 · -13 tokens per session 6392f0a7f704
- 4d ago First seen · 49 lines · 58 tokens per session scan A 9ec43f8b252e
clean-and-true is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 45 tokens to every session and 754 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 2026-09-03.
Other skills, from other repositories
askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via /askme.
slicing-code-context
Use when an exact symbol, path, entrypoint, or line range can bound a focused code question or patch proposal under a fixed source budget. Not for source changes or broad repository exploration.
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.
autopilot
Run a hands-off plan-to-ship pipeline by chaining existing skills. Use when the user says "autopilot", "take this from plan to shipped", "run the whole pipeline", "hands-off ship it", or "do the end-to-end build".
llm-self-loop
Use when a button click, dashboard check, or human verdict sits inside an iteration loop. Replaces it with an autonomous gate or moves non-automatable work outside the loop. Don't use for remote, credential, publish, deploy, or irreversible changes.
catchup
Use when the human returns after a gap, cannot follow the project, asks what happened, or wants a visual HTML recap page. Not for onboarding: use onboard. Not for handoff: use handoff.