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 complexity-grillgit 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/complexity-grill)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/complexity-grill"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/complexity-grill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.00622 |
| Opus 5 | $0.00015 | $0.00311 |
| Sonnet 5 | $0.00006 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
complexity-grill 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 yesterday.
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:
- complexity-grill — 100% identical, 2 lines differ
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.
Complexity grill
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to identify the true sources of complexity qualitatively before counting metrics. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output only: a qualitative complexity-source report with ranked root causes. |
| Done | True complexity sources are identified qualitatively and ranked before any metric is counted. |
Inputs
The code region, module, or design surface to analyze must be supplied. Optional: a named concern to weight (coupling, hidden state, leaky abstraction, special-case proliferation, accidental concurrency, premature generality, indirection exceeding what it hides). No metric input is accepted before the qualitative ranking is settled.
Procedure
- Bound scope to the named region and read it. Do not mutate anything. Done when: the region is read and scope is bounded.
- Enumerate candidate complexity sources qualitatively. For each, state where it lives and what effort it forces: coupling that blocks independent change, hidden state that must be tracked by hand, leaky abstractions, special-case proliferation, accidental concurrency, premature generality, or indirection that exceeds the complexity it hides. Done when: every candidate source is named with its location and forced effort.
- Rank candidates by the real cognitive or maintenance effort they force, not by any numeric metric. Break ties by root cause: a source that produces other sources ranks above a symptom it creates. Done when: candidates are ranked by effort with root-cause tie-breaking.
- Only after the qualitative ranking is settled, optionally attach a metric to confirm a ranked source. Metrics confirm; they never discover, reorder, or lead the ranking. If no metric is available, the ranking stands on its qualitative evidence. Done when: a metric is attached as confirmation or the ranking stands on qualitative evidence alone.
- Return the ranked report. Done when: the ranked report is returned.
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.
- yesterday Changed · -17 tokens per session f48ef6ef5543
- 3d ago First seen · 39 lines · 47 tokens per session scan A b2902ae6c3f5
complexity-grill is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 622 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
create-pull-request
Use when asked to create or update a PR, revise its description, or link issue references to its body. Not for multi-PR stacks: use gate-and-merge. Not for releases: use git-workflow-and-versioning.
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".
gate-and-merge
Use when landing a queue of open PRs: gate each PR, sweep its review feedback to root cause, then merge, repair, hold, or close it. Human-only.
doubt-driven
Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.
pr-review-canvas-html
Use when asked to render a GitHub PR as a standalone review HTML page. Fetches PR data via gh API, renders diffs with move detection, and serves the artifact on a local port. Not for Cursor Canvas output — use pr-review-canvas.
review
Use when asked to review a pull request, examine code changes, find bugs, or audit a branch. Standard mode produces a severity-graded validated-findings report with concrete fixes; depth mode fans out parallel bug/security and quality reviewers and synthesizes a unified verdict. Not for an iterative review-and-fix…