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 agentmods add skills/hoavdc/codexkit/codexkit-meeting-action-routernpx skills add hoavdc/CodexKit --skill codexkit-meeting-action-routergit clone --depth 1 https://github.com/hoavdc/CodexKitWrote 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/hoavdc/codexkit/codexkit-meeting-action-router)<a href="https://agentmods.dev/skills/hoavdc/codexkit/codexkit-meeting-action-router"><img src="https://agentmods.dev/badge/skills/hoavdc/codexkit/codexkit-meeting-action-router.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.00583 |
| Opus 5 | $0.00030 | $0.00292 |
| Sonnet 5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
codexkit-meeting-action-router 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 6d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Action Router
Purpose
Convert raw meeting material into a tight recap that people can execute.
When to use
- a meeting ended with messy notes
- different attendees are likely to remember different outcomes
- the team needs a recap and owner list fast
When not to use
- the user needs a strategy memo or a recommendation
- the source material is too incomplete to identify real decisions
Inputs
- notes, transcript, or bullet summary
- attendee list if known
- target recap style if one exists
Procedure
- Separate confirmed decisions from discussion.
- Extract action items with owners and dates when present.
- Mark assumptions where owner or due date is missing.
- Group open questions that still need a follow-up.
- End with a short recap paragraph ready to send.
Output
- decisions made
- actions with owners and dates
- unresolved questions
- recap paragraph or draft message
Definition of done
- a reader can tell what happened without rereading the notes
- every real action has an owner or a gap flag
- the recap is short enough to send as-is
Examples
- "Turn these meeting bullets into a clean recap with owners."
- "Read this transcript and give me decisions, actions, and open questions."
Quality Criteria
- Trigger conditions and input requirements are unambiguous
- Each automated step produces a verifiable output
- Error handling and fallback paths are defined
- Manual override points are documented
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Does the workflow produce the expected output for the defined inputs? |
| Completeness | Are all trigger conditions, edge cases, and error paths handled? |
| Context-fit | Is the automation appropriate for the frequency and criticality of this task? |
| Consequence | If this ran unattended and failed silently, what would the downstream impact be? |
Edge Cases
- Input format varies unexpectedly — Add a normalization step at entry. Alert the operator on format mismatches.
- Downstream system is unavailable — Queue the output and retry with exponential backoff. Alert after N failures.
- Partial execution completes — Ensure idempotency — re-running from the start produces the same result without duplication.
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.
- 6d ago First seen · 82 lines · 60 tokens per session scan A 259c82f44be4
codexkit-meeting-action-router is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 583 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 2026-08-30.
Other skills, from other repositories
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…
checking-code-quality
Checks code quality metrics including complexity, duplication, naming conventions, and function length. Use when running quality gates, reviewing code smells, or checking lint rules. Automatically triggered on complex modules or post-refactor.
cultivating-personas
Distills AI agent voice patterns from conversation into a Persona Voice Card v1.0 (self/user/language/register/emojipolicy/flourish only — no judgment-shaped fields), validates schema + content safety + differentiation, and routes contributions through the existing submission portal. Use when the user wants to…
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…