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 feedback-pattern-sweepgit 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/feedback-pattern-sweep)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/feedback-pattern-sweep"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/feedback-pattern-sweep/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/feedback-pattern-sweep"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/feedback-pattern-sweep.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 | $0.00054 | $0.00864 |
| Opus 5 | $0.00027 | $0.00432 |
| Sonnet 5 | $0.00011 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
feedback-pattern-sweep 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback pattern sweep
Contract
| Field | Bound contract |
|---|---|
| Trigger | Recent resolved feedback may reveal a broader recurring defect pattern. |
| Authority | Reversible local: write only named local artifacts; state and follow the rollback path before mutating. |
| Side effect | Root-cause pattern sweep over recent resolved feedback; local writes limited to the declared bound. |
| Done | All root-cause clusters checked, every confirmed recurrence addressed, and a fresh search finds no generalized recurrence. |
| Stop | Stalled; blocked; exhausted; capped. Bound: declared feedback window and project surface. |
Inputs
- Feedback window (required): which resolved items to sweep, bounded by date range or item list.
- Project surface (required): the path or glob set to search for recurrence.
- Budget (required): the effort or time limit, declared before work begins.
Procedure
- Bind the feedback window, project surface, and budget. Freeze all three before any mutation. Done when: the window, surface, and budget are named and frozen.
- Sweep the resolved feedback inside the window for shared root causes. For each resolved item, extract the defect description and the fix applied. Cluster items that trace to one root cause by matching the underlying fault pattern, not the surface symptom. Mark items that share no root as isolated. Done when: every resolved item in the window is classified by root cause or marked isolated.
- For each root-cause cluster, search the project surface for generalized recurrence. Use word-boundary search for the root-cause pattern: the code shape, the missing check, the wrong assumption, or the invariant violation that produced the original defect. Record each hit with its file, line, and the root-cause cluster it matches. Done when: every root cause has a recurrence result (found and addressed, or confirmed absent).
- Triage and address confirmed recurrences. For each hit, confirm the root-cause pattern applies by reading the surrounding code. Apply the minimal fix that removes the fault class, the same root-shape repair that resolved the original feedback. Do not patch the symptom; remove the pattern. Done when: every confirmed recurrence is addressed or explicitly deferred with a reason.
- Verify absence. Run a fresh search over the project surface for each root-cause pattern. Confirm zero remaining hits. Done when: the fresh search finds no generalized recurrence, or remaining hits are justified exclusions with recorded reasons.
- Stop at success (all recurrences addressed and verified absent), any non-success terminal, or the bound. Done when: a terminal class is reached and named.
- Persist the run record to
.outline/loops/feedback-pattern-sweep/<run_id>/when durable. Emitreceipt.jsonbefore return. Done when: the receipt is written with the terminal class, root-cause clusters, per-root recurrence results, and verification status.
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 · 45 lines · 54 tokens per session scan A 16c390347013
feedback-pattern-sweep is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 54 tokens to every session and 864 once invoked, about $0.0003 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.