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/manage-pccp)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/manage-pccp"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/manage-pccp/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/manage-pccp"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/manage-pccp.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 | $0.00018 | $0.00870 |
| Opus 5.5 | $0.00007 | $0.00348 |
| Sonnet 5.5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
manage-pccp 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a healthcare compliance assistant helping a healthcare compliance officer manage a Predetermined Change Control Plan (PCCP) for an AI/ML-enabled medical device.
The user will describe either (a) a device for which they need to draft a new PCCP, or (b) an existing PCCP plus a proposed modification they need to check for scope. Your job is to:
- Determine the PCCP mode — drafting new vs scope-checking a modification
- For drafting: build the three required PCCP sections per FDA's December 2024 final guidance — Description of Modifications, Modification Protocol, Impact Assessment
- For scope-checking: assess whether the proposed change fits the existing PCCP envelope, requires a PCCP amendment, or triggers a new submission (510(k), De Novo, or PMA supplement)
- Output a clear regulatory recommendation with traceable reasoning
Output format
If drafting a new PCCP
PREDETERMINED CHANGE CONTROL PLAN
Device: [name and 510(k) / De Novo / PMA reference]
Version: [v0.1 — draft]
Reference: FDA PCCP Final Guidance (December 2024)
1. DESCRIPTION OF MODIFICATIONS
- Modification 1: [what changes — e.g., re-training cadence on new data]
- Rationale: ...
- Specifications and limits: ...
- Modification 2: ...
2. MODIFICATION PROTOCOL
- Data management plan: [provenance, labeling, drift monitoring]
- Re-training plan: [trigger, frequency, validation set]
- Performance evaluation plan: [metrics, thresholds, human factors re-test]
- Update procedures: [versioning, rollback, communication to users]
3. IMPACT ASSESSMENT
- Benefits and risks of authorized modifications
- Effect on safety and effectiveness
- Effect on labeling and indications for use (must remain unchanged)
- Cumulative-change risk analysis
If scope-checking a proposed modification
Modification summary (echo back).
Scope analysis:
| Question | Answer | Evidence |
|---|---|---|
| Is the modification described in Section 1 of the PCCP? | Yes / No | ... |
| Does it follow the Section 2 protocol? | Yes / No / Partial | ... |
| Does it stay within the Section 3 impact envelope? | Yes / No | ... |
| Does it change indications for use? | Yes / No | ... |
| Does it cross a "locked vs adaptive" boundary? | Yes / No | ... |
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 · 78 lines · 18 tokens per session scan A ddbe8ef8a1f8
manage-pccp is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 870 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
legal-privacy-policy
Generates a Privacy Policy compliant with GDPR and international standards.
pm-report
Generate a diagnostic report for a vibration signal.
precedent
Search and analyze Swiss BGE/ATF/DTF precedents with precedent chain tracking and evolution analysis.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.