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-critiquegit 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-critique)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cross-critique"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cross-critique/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-critique"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cross-critique.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 | $0.00038 | $0.01003 |
| Opus 5 | $0.00019 | $0.00502 |
| Sonnet 5 | $0.00008 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
cross-critique 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cross-critique — 91% identical, 0 lines differ
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.
Cross critique
Contract
| Field | Bound contract |
|---|---|
| Trigger | Multiple independent proposals on a contested decision exist (round-one proposals are on the table). |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. The synthesis is conversational output. |
| Side effect | Read-only second round reusing existing subagents; no repo mutation. |
| Done | Synthesis notes convergence, strongest objections, and surviving option. |
Inputs
- N independent proposals from a prior round (must be supplied). Round one must have been independent (authors did not see each other's work) or the diversity that makes round two valuable is lost.
- The contested decision question and its decision criteria (must be supplied).
- Access to the same subagents that produced round one (required, to reuse their investigation context).
- Optional: neutral authorship labels (Proposal A, B, C) for anonymized circulation.
Procedure
- Verify the prerequisite: at least two genuinely divergent proposals exist from an independent first round. If the proposals already strongly agree, or the question has an objective answer verifiable directly, stop. A second round adds latency and tokens without resolving real disagreement. Done when: divergence and independence are confirmed, or the round is stopped with the reason reported.
- Assemble each proposal's core recommendation and reasoning (not full transcripts). Label them neutrally (Proposal A, B, C) and anonymize authorship where practical to reduce bandwagon bias toward whichever author sounds most confident. Done when: each proposal is assembled with neutral labels and anonymized authorship.
- Reuse the same subagents from round one rather than spawning fresh ones, so each retains its investigation context. Send each author only the other proposals (not its own). Done when: each round-one subagent is reused and receives only the other proposals.
- Ask each author to assess every alternative:
- Its pros: what it gets right and where it is stronger than the author's own approach.
- Its cons: risks, edge cases, hidden costs, and wrong assumptions.
- Whether the alternatives change the author's recommendation, and why or why not.
- A final ranking with confidence.
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 · -11 tokens per session 25f489b2ce2f
- 5d ago First seen · 54 lines · 49 tokens per session scan A 5c4bba855587
cross-critique is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,003 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.