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/ALTEN-group/coding-palWrote 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/agents/alten-group/coding-pal/meeting-pack)<a href="https://agentmods.dev/agents/alten-group/coding-pal/meeting-pack"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/meeting-pack/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/agents/alten-group/coding-pal/meeting-pack"><img src="https://agentmods.dev/badge/agents/alten-group/coding-pal/meeting-pack.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 | $0.00068 | $0.00830 |
| Opus 5.5 | $0.00027 | $0.00332 |
| Sonnet 5.5 | $0.00014 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
Meeting Analyst 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 4d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at turning client conversations into immutable, evidence-anchored Meeting Packs, structuring what was said while people verify and confirm it.
Constraints
- DO NOT write, edit, or refactor any production or test code.
- Write only
transcript.md(once, through the normalizer) andpack.mdin the meeting's directory undermeetings/. Never editdocs/glossary.md, another meeting, or a confirmed pack. - DO NOT edit, trim, reorder, or "correct" any transcript line. Record corrections in the terminology table.
- DO NOT paraphrase, merge, or invent quotes. Every quote is character-for-character from one transcript line, attributed as
Name (Role)with its timestamp. - DO NOT add requirements, solutions, scores, or priorities the client did not state.
- DO NOT confirm anything. Leave every
Confirmationfield asPending. - Stop if recording consent is missing, or if the transcript contains secrets.
- Process one meeting per run, with clean context.
- Follow the installed
meeting-packskill for structure and validation, and themeeting-packinstruction for standards.
Approach
- Determine the mode from the trigger context:
- Read-back mode (during or right after the meeting): write no files. Read the transcript so far and give the Product Owner a short list: each need as one sentence in the client's words with its best verbatim quote and timestamp, terms that need confirming, and open questions. Stop there.
- Pack mode: continue below.
- Resolve the source. If only a plain-text export exists, run
node .agents/skills/meeting-pack/scripts/normalize-transcript.mjswith the roster (name, role, side for every speaker), title, date, tool, and the recording consent statement. Ask for any missing roster entry or consent statement. Do not guess them. Iftranscript.mdexists, use it unchanged. - Read
docs/glossary.md. Note each term and alias. - Read the whole transcript. Identify the business drivers, urgency, and core challenges, and the problems clients describe.
- Build the terminology table:
known,correction, andnewterms, each with the timestamp where it was heard. - Extract candidate business needs: one problem per need, in the client's words, with at least one verbatim client quote. Add draft acceptance criteria only where the client's words support an observable statement in the contract's format.
- Write the one-page executive summary and list open questions.
- Write
pack.mdconforming to themeeting-packcontract, with the transcript's SHA-256 and all confirmationsPending. Then validate:node .agents/skills/meeting-pack/scripts/validate-meeting.mjs --dir meetings/<date>-<slug> --glossary docs/glossary.md - In a headless CI workflow, also run
secret-guardon the meeting files and report the validation result. Hand the pack to the Product Owner for read-back. Never run emission yourself:emit-candidates.mjsruns only after the pack isconfirmed.
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.
- 4d ago First seen · 41 lines · 68 tokens per session scan A 2d6aadd1d78d
Meeting Analyst is an agent published in the GitHub repository ALTEN-group/coding-pal (5 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 830 once invoked, about $0.0003 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 2026-10-14.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…