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 exhaustivegit 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/exhaustive)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/exhaustive"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/exhaustive/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/exhaustive"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/exhaustive.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 | $0.00077 | $0.01255 |
| Opus 5 | $0.00039 | $0.00628 |
| Sonnet 5 | $0.00015 | $0.00251 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
exhaustive 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exhaustive
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user says "exhaustive", "prove coverage", "did I miss any case", "enumerate the state space", or asks for a completeness audit before done. |
| Authority | Reversible-local: read-only on the target source; the only write is the coverage manifest artifact, whose rollback is discarding or deleting that file. |
| Side effect | Writes one classified coverage manifest (human-readable or exhaustive-manifest/v1 YAML) with gaps prepared in dependency order; no source, VCS, config, or remote mutation. |
| Done | The manifest has zero unclassified cells and a one-line tally; for code state spaces the wildcard-catch-all assertion holds. |
Inputs
- Must be supplied: the target surface to audit — a code area, a spec or feature, a design with open forks, or a refactor/deletion scope.
- Optional: a request for machine-readable
exhaustive-manifest/v1output; user-applied fixes to individualgapcells (each triggers exactly one re-enumeration). - If the target space is unbounded or unidentifiable after one read, stop and ask one question to bound it; do not enumerate an infinite space.
Procedure
-
Choose and name the enumeration that fits the target; restate the choice in the output so the reader knows which space was covered:
- State space — code with lifecycle, state machines, or error paths: the State × Event × Outcome Cartesian matrix.
- Decision space — a design with open forks: the dependency-respecting set of decision axes.
- Requirement space — a spec or feature: the requirement-to-symbol map, each acceptance criterion traced to a code or test symbol.
- Behavior surface — a refactor or deletion: every exported symbol and reachable path in scope.
Enumeration is algorithmic and single-pass; it is not round-based questioning or hypothesis sampling. Done when: the enumeration type is chosen, named, and restated.
-
Enumerate the full cell list for the chosen space with tool-backed discovery: structural search for code constructors and match arms, reference search for symbols and callsites, direct reads for spec criteria. Every cell carries an
idand a one-line description. The list is the universe: nothing outside it is in scope, and nothing inside it may be silently dropped. Done when: the full cell list is enumerated with every cell carrying an id and description.
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 · 55 lines · 77 tokens per session scan A 9f8ef33f1ac3
exhaustive is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,255 once invoked, about $0.0004 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
libfuzzer
Use when asked to build, run, or triage a coverage-guided C/C++ fuzz campaign on the libFuzzer or AFL++ engine. Not for harness design: use fuzz-harness-writing.
strict-validation-setup
Use when a user invokes a strict-mode validation or verifiable-goals loop setup. Bootstraps strict-mode tooling and per-task GOALS.md scaffolding so an agentic loop can self-verify. Don't use for remote, credential, publish, deploy, or irreversible changes.
oss-fuzz
Use when enrolling a project in OSS-Fuzz, running its helper workflow locally, or reproducing an OSS-Fuzz report. Not for remote, credential, publish, deploy, or irreversible changes.
validation-first-driven
Use when building protocols, workflows, concurrent systems, or lifecycle-heavy state that needs explicit states, transitions, and temporal properties. Defines the state machine, encodes invariants in types, and for high-risk designs runs a TLA+ or Alloy model checker. Not for encoding domain models in types — use…
testing-handbook-generator
Use when the user asks to discover, generate, refresh, or validate skills from the Trail of Bits Testing Handbook or appsec.guide. Not for tasks that require source or remote-system changes.
ios-device-qa
Use when the user runs /ios-device-qa to drive a real iPhone over USB through a debug-bridge daemon and return a device QA report with verified interactions. Do not use for remote, credential, publish, deploy, or irreversible changes.