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 cross-run-playbookgit 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/cross-run-playbook)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cross-run-playbook"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cross-run-playbook/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/cross-run-playbook"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cross-run-playbook.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 | $0.00036 | $0.00682 |
| Opus 5 | $0.00018 | $0.00341 |
| Sonnet 5 | $0.00007 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
cross-run-playbook 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-run playbook
Contract
| Field | Bound contract |
|---|---|
| Trigger | A long agentic project where each cycle must produce a learning memo before the next pass begins. |
| Authority | Reversible local: writes only named local artifacts; rollback is version control or undo. No remote mutation. State the rollback path for each write. |
| Side effect | Builds vertical slices, runs real-surface drives, produces memos and gates; versions only quality-cleared templates or modules. |
| Done | Real surface driven with evidence captured; memo names at least one lesson, anti-pattern, or gate affecting the next pass; keep/iterate/restart decision explicit; version labels only on quality-cleared artifacts. |
Inputs
Required: a framed thesis with named quality gates for the first pass, or a previous-cycle memo for subsequent passes.
Procedure
- Build one complete vertical slice against the framed thesis and its quality gates. Done when: one complete vertical slice is built against the thesis and gates.
- Drive the slice through the real surface: browser for web apps, HTTP for API contracts, CLI for data-shaped artifacts, or the application entry point for desktop apps. Done when: the slice is driven through the real surface.
- Capture evidence from the real-surface drive. Done when: evidence from the real-surface drive is captured.
- Extract lessons, anti-patterns, and next-cycle gates. Name at least one finding that affects the next pass. Done when: at least one lesson, anti-pattern, or gate affecting the next pass is named.
- Make an explicit keep/iterate/restart decision. If the decision is restart, carry the lessons forward but leave failed code behind. Done when: the keep/iterate/restart decision is explicit, with lessons carried forward on restart.
- Subject the next plan to an adversarial review or human-invoked attack before building it. Done when: the next plan is subjected to adversarial review or human-invoked attack.
- Version only templates or modules that clear their quality gates. Done when: version labels are applied only to quality-cleared templates or modules.
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.
- 2d ago Changed · -25 tokens per session 45f7df850780
- 4d ago First seen · 39 lines · 61 tokens per session scan A 51d613299e87
cross-run-playbook is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 682 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.
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.