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 audit-loop-scaffoldgit 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/audit-loop-scaffold)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/audit-loop-scaffold"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/audit-loop-scaffold/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/audit-loop-scaffold"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/audit-loop-scaffold.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 | $0.00034 | $0.01223 |
| Opus 5.5 | $0.00014 | $0.00489 |
| Sonnet 5.5 | $0.00007 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
audit-loop-scaffold 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 28d 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:
- audit-loop-scaffold — 100% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit loop scaffold
Contract
| Field | Bound contract |
|---|---|
| Trigger | Loop scaffold files have drifted from their templates or from each other |
| Authority | Reversible local: writes only the four named auto-fixable files; rollback is restoring retained pre-write content. No remote mutation. Retains pre-write content (including the absence state for newly created files) and rolls back on verification failure. |
| Side effect | Rewrites only STATE.md, gate.yaml, loop-budget.md, loop-run-log.md from templates; reports every other drifted file |
| Done | Scaffold files match their templates or drift is reported with its exact file; nothing outside the fixed set was written |
Inputs
| Input | Required | Description |
|---|---|---|
| loop_dir | yes | path to the loop directory containing scaffold files |
| templates | yes | STATE.md.template, gate.yaml.template, loop-budget.md.template, loop-run-log.md.template from the loop-engineering provenance |
Templates must be sourced from cobusgreyling/loop-engineering at revision d03dcb92. No other skill, module, AGENTS file, or planning artifact is required.
Procedure
- Resolve
loop_dirto an absolute path. Fail withloop_dir_unavailableif it does not exist or is not a directory. Done when:loop_dirresolves to an existing directory. - Read the four template files into memory. Fail with
template_unavailableif any template cannot be read. Done when: all four templates are in memory. - List every file in
loop_dirat depth 1 (direct children only). Done when: the direct-child file list is complete. - Back up pre-write state for the four auto-fixable files. For each name (STATE.md, gate.yaml, loop-budget.md, loop-run-log.md): if the target file exists, record its content and hash; if it does not exist, record its absence. This backup is the rollback source. Done when: pre-write state for all four auto-fixable files is recorded, including absence states.
- Converge the four files to template content. For each auto-fixable name:
a. Compute the target path as
loop_dir/<name>. b. If the target does not exist or its hash differs from the template hash, write the template content to the target path. c. Record the write in the action log with before/after hashes andbefore_contentcopied from the step-4 backup (null for newly created files). Done when: every auto-fixable file matches its template or is written from it, and before/after hashes are recorded. - For every other file in
loop_dirnot in the auto-fixable set: compute the file hash. If the hash matches none of the four template hashes, record the file path and hash in the drift report. Done when: every non-auto-fixable drifted file is in the drift report. - Verify every written auto-fixable file matches its template byte-for-byte by re-reading and comparing hashes. If any verification fails, roll back every file written in step 5 to its pre-write content from the step 4 backup: restore existing files to their recorded content, and delete files that were newly created (whose pre-write state was absence). Fail with
auto_fix_verify_failed. Done when: every written file matches its template byte-for-byte. - Assert: every auto-fixable file matches its template; every other drifted file is in the drift report. If the assertion fails, fail with
non_converged. Done when: the assertion holds. - Return the complete drift report. Done when: the drift 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.
- 28d ago Changed · +1 lines e33124cd8ad0
- 1mo ago Changed · +1 lines bc015b144ef6
- 1mo ago Changed · -41 tokens per session 0f9a4da929c3
- 1mo ago First seen · 84 lines · 75 tokens per session scan A c927acaa1677
audit-loop-scaffold is a skill published in the GitHub repository OutlineDriven/outline-driven-development (54 stars, last pushed 28d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,223 once invoked, about $0.0001 per session on Opus 5.5. 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".
optimize
Use when asked to optimize code, make a path faster, make this as fast as possible, reduce allocations, repair a regression, profile a target, grill every inefficiency, or run a subsystem or repo-wide performance campaign against a measured floor; when a performance requirement, slowness report, Core Web Vitals miss…
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.
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.
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.
extremely-optimize
Use when asked to run a performance campaign against a measured floor. Not for hypothesis-only analysis without mutation: use fastopt.