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 magnus919/agent-skills --skill firefliesgit clone --depth 1 https://github.com/magnus919/agent-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/magnus919/agent-skills/fireflies)<a href="https://agentmods.dev/skills/magnus919/agent-skills/fireflies"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/fireflies/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/magnus919/agent-skills/fireflies"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/fireflies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01016 |
| Opus 5 | $0.00044 | $0.00508 |
| Sonnet 5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
fireflies 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 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.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fireflies.ai
Use scripts/fireflies from this skill directory. It uses the Fireflies GraphQL endpoint directly
and emits the API response as JSON. Read-only discovery is safe. Before any state change, confirm
the target, scope, and rollback path; then route the change through the CLI's literal --confirm.
--dry-run previews a payload only and never authorizes a write.
First Use
- Check the command schema:
scripts/fireflies --helpand the relevant subcommand help. - Set
FIREFLIES_API_KEYonly for an actual API request. Do not expose or persist it. - Start with read-only discovery, such as
scripts/fireflies transcripts list --limit 10 --json. - Use
--dry-run --jsonbefore each mutation to inspect the exact GraphQL payload.
Command Map
| Need | Command |
|---|---|
| Find transcript metadata | scripts/fireflies transcripts list --keyword TEXT --limit 10 --json |
| Read a meeting, summary, sentences, analytics, and recording links | scripts/fireflies transcripts get ID --json |
| People, channels, groups, contacts, apps | users, channels, groups, contacts, apps |
| Meeting analytics or live meetings | analytics --start DATE --end DATE, meetings active |
| Ask a transcript question | askfred create --question TEXT --transcript-id ID --confirm |
| Read one AskFred thread | askfred get THREAD_ID |
| Assign an admin/user role | users set-role --user-id ID --role admin --confirm |
| Move meetings into a channel | meetings update-channel --channel-id ID --transcript-ids A,B,C --confirm |
| Add a live meeting by link | live add-to --meeting-link URL --confirm |
| Create a soundbite clip | live soundbite --meeting-id ID --prompt TEXT --confirm |
| Two-phase file upload | audio create-upload ... --confirm then audio confirm-upload --meeting-id ID --confirm |
| Run an exact current/future API operation | query --document GRAPHQL --variables JSON |
| Verify a delivered webhook locally | webhook verify --secret SECRET --signature sha256=... --body FILE |
What ships with it
10 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.
- evals/evals.json 4.9 KB
- README.md 2.0 KB
- references/api-reference.md 3.9 KB
- references/cli-reference.md 2.1 KB
- references/source-index.md 2.0 KB
- references/troubleshooting.md 1.0 KB
- references/webhook-security.md 790 B
- references/workflows.md 2.7 KB
- scripts/fireflies 30 KB
- tests/test_fireflies.py 9.5 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 · 79 lines · 88 tokens per session scan A 5198114f56f5
fireflies is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,016 once invoked, about $0.0004 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
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.
government-writing
A skill for writing formal Chinese government documents, including notices and opinions, in the required official format.
ima-skills
Tencent IMA OpenAPI skill for notes and knowledge-base operations. Use after the user connects IMA in Pinvou Plugin Center.
visualizer
A skill for turning structured data, spreadsheets, and business metrics into HTML charts and dashboards using Chart.js, a JavaScript charting library.
pptx
A local generator for editable PowerPoint presentation files, including slides with text, charts, tables, and images.
meter-invoice
Generate CocoMeter chargeback invoices. Usage: $meter invoice.