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 diagnose-loop-healthgit 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/diagnose-loop-health)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/diagnose-loop-health"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/diagnose-loop-health/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/diagnose-loop-health"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/diagnose-loop-health.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 | $0.00042 | $0.00739 |
| Opus 5 | $0.00021 | $0.00369 |
| Sonnet 5 | $0.00008 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
diagnose-loop-health 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 3d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose loop health
Contract
| Field | Bound contract |
|---|---|
| Trigger | A configured loop misbehaves, or the user asks whether the loop setup is sound |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | A severity report with at most three prioritized actions and a nonzero exit on blocked; no file mutation |
| Done | Severity is healthy, warning, or blocked with exit 0, 1, or 2, and each finding names the exact missing or stale charter, state, gate, or budget file |
Inputs
The user must supply the loop directory to inspect. No file is created or written. The skill reads four file classes from that directory: the charter file, the state file, the gate file, and the budget file. If the directory is not named, ask for it and stop until it is supplied.
Procedure
-
Obtain the loop directory from the user. If absent, stop and ask; do not infer or create one. Done when: the loop directory is supplied or the skill stops to ask.
-
Bound scope to read-only inspection of that directory. Do not write, create, rename, delete, or move any file. Done when: scope is bounded to read-only inspection.
-
Locate and read the loop's charter file, state file, gate file, and budget file. For each, record presence and freshness: missing if absent; stale if its content does not match the loop's declared cadence, gate thresholds, or budget limits. Done when: all four files are read with presence and freshness recorded.
-
Classify severity on the ladder: healthy if all four files are present and current; warning if any file is missing or stale but the loop can still run; blocked if a required charter or state file is absent or unreadable. Done when: severity is classified healthy, warning, or blocked.
-
For warning or blocked, emit at most three prioritized actions ordered by impact, each naming the exact missing or stale file by path and class. Done when: zero to three prioritized actions are emitted, each naming the file by path and class.
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.
- 3d ago Changed · -36 tokens per session 06e5c98c4a59
- 5d ago First seen · 44 lines · 78 tokens per session scan A a72c21797b6f
diagnose-loop-health is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 42 tokens to every session and 739 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".
debug
Hypothesis-driven debugging. Use when a test fails, a crash or exception occurs, output is wrong, or an intermittent flake has no obvious cause.
optimize
Use when asked to optimize code, speed up a path, reduce allocations, repair a regression, or profile a target. Not for remote, credential, publish, deploy, or irreversible changes.
ios-build-fix
Use when asked to run /ios-build-fix to fix a failing iOS build, regenerate an Xcode project from project.yml, or correct UI behavior. Not for a clean rebuild: use ios-build-cleanup.
strike-the-root
Use when a bug, failure, flake, regression, review finding, or ticket needs the core fixed so it cannot recur. Not for greenfield features: use tdd. Not for style-only review or typo-class one-liners.
extremely-optimize
Use when asked to run a performance campaign against a measured floor. Not for hypothesis-only analysis without mutation: use fastopt.