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 KirKruglov/claude-project-manager --skill generate-meeting-protocolgit clone --depth 1 https://github.com/KirKruglov/claude-project-managerWrote 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/kirkruglov/claude-project-manager/generate-meeting-protocol)<a href="https://agentmods.dev/skills/kirkruglov/claude-project-manager/generate-meeting-protocol"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-project-manager/generate-meeting-protocol/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/kirkruglov/claude-project-manager/generate-meeting-protocol"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-project-manager/generate-meeting-protocol.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 | $0.00115 | $0.03237 |
| Opus 5 | $0.00057 | $0.01618 |
| Sonnet 5 | $0.00023 | $0.00647 |
| Haiku 4.5 | $0.00012 | $0.00324 |
Grade A, and why
generate-meeting-protocol 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 12d 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
98% identical to generate-meeting-protocol — 14 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
generate-meeting-protocol
Triggers
Russian: «оформи протокол», «протокол встречи», «обработай заметки со встречи» English: "generate meeting protocol", "meeting notes", "meeting minutes"
Language Detection
Determine the language of the user's request:
- If the request is in Russian → use templates with
-rusuffix - Otherwise → use templates with
-ensuffix
All output (headings, labels, comments, instructions) must match the detected language.
1. Input Data
| Data | Required | Source | Notes |
|---|---|---|---|
| Meeting notes | yes | chat or knowledge | Any format: bullet points, free text, chat copy, voice dictation. Agent structures the content independently |
| Project plan | no | knowledge | If available — agent links changes to plan element IDs (WP-xxx, Mx). If not — describes changes as text |
| Meeting context | no | chat | Meeting type, participants, date — if not included in the notes |
If required data is missing — request it (system-prompt-draft.md §3 p.2):
To generate a protocol, meeting notes are required — in any format:
bullet points, free text, chat copy, voice dictation (as text).
Minimum to start: what was discussed and what decisions/tasks were recorded.
Available data: [list what is available].
Missing: [specify].
2. Execution Algorithm
- Validate input data. Check if notes are present. If not → request using the template from §1. Do NOT generate a placeholder protocol — respond ONLY with the data request.
- Extract meeting metadata. From notes or context: date, participants, topic, meeting type, facilitator. What cannot be extracted — ask the user specifically. Minimum to proceed: meeting date.
- Structure the content. Extract from notes and categorize:
- Agenda — topics that were discussed.
- Decisions — recorded decisions (IDs: D001, D002, ...).
- Action items — actions with owners and deadlines (IDs: A001, A002, ...).
- Plan changes — if notes imply changes to timelines, scope, or resources.
- Open issues — unresolved questions requiring further discussion.
- Verify action item completeness. Each action item (A00x) must include: description, owner, deadline. If deadline/owner is missing from the notes — mark as
[clarify]and record in assumptions. - Determine plan changes (section 5). Rules:
- If project plan is available in knowledge → find affected elements, specify IDs (WP-xxx, Mx). Columns: "Was" (from plan) → "Becomes" (from notes) → "Basis" (decision ID D00x).
- If project plan is NOT available → describe changes as text without IDs. Record assumption: "Project plan not provided — element IDs not specified."
- If no plan changes → delete section 5.
- Determine conditional sections (5, 6, 7). Delete a section if no data is available for it:
- Section 5 "Plan Changes" — delete if notes contain no plan-level changes.
- Section 6 "Open Issues" — delete if all issues are resolved.
- Section 7 "Next Meeting" — delete if date/topic were not discussed.
- Read the template
meeting-protocol-{lang}.mdfrom project knowledge. - Fill template sections per the rules in section 3.
- Validate the result using the checklist (section 5).
- Show the result in chat. Format (system-prompt-draft.md §3 p.4):
- What was done: "Protocol generated for meeting [date] based on: [notes source]."
- Key outcomes: N decisions, M action items, K plan changes (or "no changes").
- Assumptions: list all.
[clarify]markers: list if any.- Next step: "Approve, provide feedback, or reject."
- Do not include system paths. Use filename only: "Protocol: meeting-protocol-YYYY-MM-DD.md".
- Wait for user response (system-prompt-draft.md §3 p.5).
- Approval → produce final text.
- Feedback → revise, show updated version. After 3rd iteration — ask: "Continue revising or finalize current version?"
- After approval:
- Propose text for insertion into log.md and project-state.md (system-prompt-draft.md §11).
- If section 5 contains changes — recommend: "The protocol includes project plan changes. Consider updating project-plan.md."
What ships with it
2 files 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.
- 12d ago First seen · 254 lines · 115 tokens per session scan A 1f3afb6b9e21
generate-meeting-protocol is a skill published in the GitHub repository KirKruglov/claude-project-manager (6 stars, last pushed 4mo ago), licensed MIT. It adds 115 tokens to every session and 3,237 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to generate-meeting-protocol, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
litigation-workflow
Civil litigation workflow expertise — case management, deposition prep, evidence chain, and Federal Rules of Evidence.
construction-management
Estimating, scheduling, building codes, safety protocols, permitting, and project controls.
stakeholder-communication
Owner reports, subcontractor coordination, RFI responses, and meeting documentation.
run-team-retrospective
Use when a team needs to reflect on a completed period, project, or significant event — to extract what worked, what didn't, and what specific changes to make before the next cycle, rather than repeating the same patterns.
project-manager
This skill has been upgraded with agentic AI capabilities, OKR/KPI integration patterns, and async-first workflows based on 2026 PM best practices research.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.