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 alexclowe/awesome-copilot-cowork-plugins --skill post-market-monitoringgit clone --depth 1 https://github.com/alexclowe/awesome-copilot-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/skills/alexclowe/awesome-copilot-cowork-plugins/post-market-monitoring)<a href="https://agentmods.dev/skills/alexclowe/awesome-copilot-cowork-plugins/post-market-monitoring"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/post-market-monitoring/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/alexclowe/awesome-copilot-cowork-plugins/post-market-monitoring"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/post-market-monitoring.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 | $0.00024 | $0.00633 |
| Opus 5.5 | $0.00010 | $0.00253 |
| Sonnet 5.5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
post-market-monitoring 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 1mo 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.
This is a copy
100% identical to post-market-monitoring — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have deep expertise in post-market monitoring of AI systems under EU AI Act Article 72, FDA AI/ML post-market guidance, and FINRA supervisory expectations. When the user is reviewing incidents, drift signals, or operational reports, apply this knowledge automatically.
Core competencies
Incident taxonomy:
- Performance degradation (concept drift, data drift, calibration loss)
- Safety incident (harm, near-miss, dignitary harm)
- Bias incident (disparate impact emerging post-deployment)
- Security incident (model extraction, prompt injection success, data exfiltration)
- Governance incident (use outside intended purpose, unauthorized population, off-label deployment)
- Hallucination / factuality failure with downstream user reliance
EU AI Act Article 73 reportable serious incidents:
- Death or serious harm to health
- Serious and irreversible disruption of critical infrastructure
- Breach of Union law obligations protecting fundamental rights
- Serious harm to property or environment
- Reporting deadlines: immediate (no later than 15 days, 2 days for widespread infringement, 10 days for death)
Clustering and pattern detection:
- Group incidents by failure mode, population, deployment surface, time window
- Distinguish single-event anomalies from systemic patterns (recommend systemic threshold: same root cause across 3+ incidents in 30 days)
- Surface protected-class concentration that suggests bias even when individual incidents seem unrelated
- Track leading indicators (calibration drift, complaint volume) before they become reportable
Remediation recommendations:
- Containment (kill switch, traffic gating, human-in-the-loop addition)
- Corrective action (re-training, prompt changes, guardrail addition, scope reduction)
- Preventive action (monitoring telemetry, re-evaluation cadence, root-cause control)
- Communication (notified body, regulator, affected users, public disclosure)
- Documentation update (technical file, QMS, risk register)
Adjacent regimes:
- FDA Predetermined Change Control Plan (PCCP) — what stays in scope vs requires new submission
- FINRA model risk monitoring obligations
- ISO/IEC 42001 nonconformity and corrective action clauses
- NIST AI RMF MANAGE function
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.
- 1mo ago First seen · 57 lines · 24 tokens per session scan A 5bceaf6c3253
post-market-monitoring is a skill published in the GitHub repository alexclowe/awesome-copilot-cowork-plugins (21 stars, last pushed 16d ago), licensed MIT. It adds 24 tokens to every session and 633 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to post-market-monitoring, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
backend-builder
A backend implementation role for Codex Project Autopilot, a workflow that coordinates project work. It builds the server-side logic and connects it to integrations according to an approved plan.
style-glassmorphism
Glassmorphism (Frosted Glass) style tokens and row template for the list-styling skill. Floating cards with soft diffused shadows, no hard borders, pill badges, thin progress bars, maximum whitespace. Layout is a single-column centered card — no sidebar split. Use when the user says "glassmorphism," "frosted glass,"…
apify-local-business-leads-osm
Build a local-business lead list without scraping Google Maps. Routes "find dentists / plumbers / salons / restaurants in with emails", "business email finder for in ", "web-design prospects with no website or a weak one", "enrich my list of business websites with verified emails", "leads within 5 km of an address"…
confluence-to-markdown
Internal fetcher module for Confluence pages. Fetches content via Atlassian MCP (preferred), REST API with Basic Auth (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:teach and /bedrock:sync — not intended for direct user invocation.
generate-site-onboarding-guide
Generate a concise Markdown onboarding guide for the current SharePoint site by inspecting its pages, libraries, lists, and navigation using read-only methods. Use when the user says: "Create an onboarding guide for this SharePoint site" "Generate a site onboarding guide" "Help new team members understand this site"…