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 figure-it-outgit 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/figure-it-out)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/figure-it-out"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/figure-it-out/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/figure-it-out"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/figure-it-out.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 | $0.00049 | $0.00661 |
| Opus 5 | $0.00024 | $0.00331 |
| Sonnet 5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
figure-it-out 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure it out
Contract
| Field | Bound contract |
|---|---|
| Trigger | Design a bespoke execution workflow when no playbook fits. |
| Authority | Write only named local artifacts built for this task; state the rollback path before writing each one. |
| Side effect | Builds and runs task-specific levers; changes limited to local artifacts named in the workflow. |
| Done | Predicate verified on real product with reviewable trail. |
Inputs
- The task to execute and the falsifiable success predicate that defines done. Required.
- Available tools and the real product surface the predicate must be verified against. Required.
- Existing playbooks or prior workflows, if any, to confirm none fits. Optional.
Procedure
- Confirm no existing playbook fits the task; if one does, stop and defer to it. Done when: no playbook fits, or the skill stops and defers.
- Define a falsifiable success predicate: a check that can fail on the real product, not a tautology. Done when: the predicate is stated and can fail.
- Design the smallest bespoke workflow that reaches the predicate: name each lever (script, command, probe, or local artifact), its input, and its expected output. Done when: every lever is named with its input and expected output.
- State the rollback path for every local artifact the workflow writes before writing it. Done when: every artifact's rollback path is stated before it is written.
- Build and run each lever in order, recording the command, the real output, and whether it advanced the predicate. Done when: every lever is run with its real output recorded.
- Verify the success predicate against the real product, not a mock or a proxy. Done when: the predicate is verified or fails on the real product.
- Assemble the reviewable trail: the predicate, each lever run with its real output, and the final verification result. Done when: the trail is assembled with predicate, lever runs, and verification result.
Failure and recovery
- No-fitting-playbook check fails: if a playbook fits, stop; do not invent a bespoke workflow.
- Predicate is not falsifiable: stop; require a predicate that can fail before proceeding.
- Lever output contradicts expected output: record the contradiction, do not advance; revise the lever or the workflow and re-run from the changed step.
- Predicate fails on real product: report the failure with the trail; do not claim done. Roll back local artifacts via the stated rollback path if the workflow left the product in a worse state.
- Blocked or non-converged result: the predicate is not verified and the trail shows which lever failed and why; no done claim is made.
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 · 42 lines · 49 tokens per session scan A 235062b1e5cd
figure-it-out is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 49 tokens to every session and 661 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
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.
snippet-image-rendering
Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.