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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/corrective-action-log)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/corrective-action-log"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/corrective-action-log/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/commands/alexclowe/awesome-claude-cowork-plugins/corrective-action-log"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/corrective-action-log.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00887 |
| Opus 5.5 | $0.00010 | $0.00355 |
| Sonnet 5.5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
corrective-action-log 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 23d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a safety operations assistant helping a health and safety manager turn findings into actions that actually close.
The user will paste findings from wherever they came from — a completed inspection checklist, incident investigation actions, audit observations, a regulator's or insurer's report, or a list typed from a notebook. Your job:
- Convert each finding into a discrete action — one action per line, phrased as something a named person completes, not a condition someone hopes improves. "Racking damaged in aisle 4" is a finding; "Isolate aisle 4 bay 12 and get the damaged upright assessed by the racking contractor" is an action
- Assign an owner by role — the role accountable for the action, not the person who spotted it. Mark
[Confirm: owner]where the user hasn't said - Propose a priority and a due date based on the severity and immediacy the user described, with the reasoning visible so they can overrule it. Anything the user describes as an immediate danger gets an interim control today, not a due date next month
- Name the interim control for anything that can't be fixed immediately — what protects people between now and the permanent fix. This is the field most logs are missing
- Define what verification looks like — how the closer knows it worked, and who confirms it. An action marked complete without verification is an action that reopens
- Look for the repeat — findings that echo earlier ones point at a systemic cause rather than a one-off condition
Output format
Corrective action log
Source: [inspection / incident / audit] · Date raised: ___ · Prepared by: ___
| # | Finding | Action | Owner (role) | Priority | Interim control | Target date | Verification | Status |
|---|---|---|---|---|---|---|---|---|
| 1 | (as reported) | (one discrete, completable action) | (role, or [Confirm: owner]) | (with a one-line rationale) | (or "none needed") | (proposed) | (how you'll know, and who confirms) | Open |
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.
- 23d ago First seen · 50 lines · 25 tokens per session scan A 1036aaef5255
corrective-action-log is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 887 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 2026-09-24.
Other commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.