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 synthesisengineering/synthesis-skills --skill synthesis-meeting-transcriptsgit clone --depth 1 https://github.com/synthesisengineering/synthesis-skillsWrote 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/synthesisengineering/synthesis-skills/synthesis-meeting-transcripts)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-meeting-transcripts"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-meeting-transcripts/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/synthesisengineering/synthesis-skills/synthesis-meeting-transcripts"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-meeting-transcripts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 204 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Rogue Agent · line 89 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00073 | $0.08082 |
| Opus 5 | $0.00036 | $0.04041 |
| Sonnet 5 | $0.00015 | $0.01616 |
| Haiku 4.5 | $0.00007 | $0.00808 |
Grade A, and why
synthesis-meeting-transcripts scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
unverifiable, separates curl transport failure from HTTP status, and prevents a How it starts
The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
v0.9.0 — The declared set gets an execution path
v0.9.0 (2026-08-29) closes the gap an external adversarial review found in v0.8.0: the policy said "declared means fetched" while the operative protocol only resolved one user-named meeting. Step 0 now defines the declared-window sweep — enumerate the declared set for the window, fetch every member, and account for every member in the report with unclosed gaps recorded machine-readably. Frontmatter version also catches up; v0.8.0 shipped with stale skill metadata.
v0.8.0 — Declared means fetched: no judgment gate before fetching
v0.8.0 (2026-08-27) removes agent judgment from the decision of which declared transcripts to fetch.
The defect. The sweep enumerated documents and recorded their ids, but fetching was gated on the agent deciding what looked worth fetching. That judgment deprioritised several meetings as routine standups. One held a live action item for the principal; another carried a launch date contradicting the one recorded everywhere else, so the corpus held two incompatible dates and nothing surfaced the conflict.
The rule. If a transcript is declared in scope for the window, it is fetched. The agent does not get a vote on which declared items are interesting. Relevance is judged after fetching, when the content is visible — never before, from a title.
Why this shape is already settled here. The workspace retired this exact failure once before, when "sync when active" gating was removed from the repo list after a repository drifted for six weeks behind a judgment that it looked inactive. Titles and activity heuristics are not evidence about content. A declared set exists precisely so that no per-item judgment stands between the list and the fetch; re-introducing one at a lower level rebuilds the failure the declared set was meant to prevent.
A run that cannot fetch a declared item records it as an unclosed gap rather than silently omitting it.
v0.7.0 — Source grade is now executable
What ships with it
18 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.
- acceptance-suite.yaml 4.4 KB
- agents/openai.yaml 270 B
- fixtures/raw-message-transcript.md 2.4 KB
- fixtures/structured-summary-128-lines.md 4.6 KB
- optional-workspace-mcp/doctor.sh 8.7 KB runs code
- optional-workspace-mcp/fetch-meeting.py 9.4 KB runs code
- optional-workspace-mcp/install-autostart.sh 5.5 KB runs code
- optional-workspace-mcp/mcp_client.py 3.3 KB runs code
- optional-workspace-mcp/README.md 4.4 KB
- optional-workspace-mcp/start.sh 4.6 KB runs code
- optional-workspace-mcp/stop.sh 771 B runs code
- optional-workspace-mcp/test_doctor.py 3.1 KB runs code
- optional-workspace-mcp/uninstall-autostart.sh 1.0 KB runs code
- test_transcript_primary.py 9.3 KB runs code
- test_verify_transcripts.py 14 KB runs code
- test_version_parity.py 1.2 KB runs code
- transcript_primary.py 18 KB runs code
- verify_transcripts.py 18 KB runs code
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.
- 10d ago First seen · 527 lines · 73 tokens per session scan A 0dbd86392b1e
synthesis-meeting-transcripts is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 8,082 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.