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 uselessspace/freedeepagents-activity-builder --skill activity-smokegit clone --depth 1 https://github.com/uselessspace/freedeepagents-activity-builderWrote 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/uselessspace/freedeepagents-activity-builder/activity-smoke)<a href="https://agentmods.dev/skills/uselessspace/freedeepagents-activity-builder/activity-smoke"><img src="https://agentmods.dev/badge/skills/uselessspace/freedeepagents-activity-builder/activity-smoke.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 | $0.00128 | $0.01269 |
| Opus 5 | $0.00064 | $0.00634 |
| Sonnet 5 | $0.00026 | $0.00254 |
| Haiku 4.5 | $0.00013 | $0.00127 |
Grade A, and why
activity-smoke 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 8d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity Smoke
<builder-root> 指从本 SKILL.md 所在目录向上两级、包含根 SKILL.md 与
tools/ 的目录；不要假定它位于目标项目的 packages/ 下。
解析 <project-python> 时遵循
../../references/python-environment.md。
何时用：活动目录同步后确认"真能跑出东西"。判定失败 → 带同一个
turn_id转/activity-diagnostician。
Dynamic verification. The smoke is "a synced activity successfully served one user turn" — not "every code path works".
Evidence standard
A turn is considered smoke-passing when its trace.jsonl contains at least
one of each of these SSE event types (assertable offline against the file):
| Event type | What it proves |
|---|---|
card_item (non-fallback) |
The activity emitted at least one real user-visible card. Cards whose payload matches the runtime zero-emit fallback signature (assignment_id="runtime-zero-emit-fallback" / card.template="runtime.zero_emit_fallback" / card.meta.kind="zero_emit_failure") do not count — they indicate the activity emitted nothing and the runtime stepped in. |
turn_completed |
The turn reached its terminal state cleanly. |
done |
The runtime signed off the SSE stream (no abrupt termination). |
Any of these missing means the turn did not complete normally; route to
activity-diagnostician with the same turn_id.
Driving the turn
The operator runs the activity manually in an environment that has:
- An FDA service (uvicorn + the runtime) reachable, OR
scripts/dev_smoke_card_system.pyfor static prompt / loop-guard checks (does not exercise emit paths).
For a real end-to-end smoke:
- Start the FDA service (
uvicorn app.main:app ...). - Open the activity in the client and send a single user message.
- The runtime writes the trace at
runtime/instances/<activity_type_id>/<instance_id>/turns/<turn_id>/trace.jsonl. - Run the parser below against that file.
This skill deliberately stops short of automating step 1-2 by itself. Different deployments have different start commands, ports, and LLM credentials. The parser + the evidence standard are the portable core.
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.
- 8d ago First seen · 118 lines · 128 tokens per session scan A 945f261e5aed
activity-smoke is a skill published in the GitHub repository uselessspace/freedeepagents-activity-builder (2 stars, last pushed 20d ago), licensed MIT. It adds 128 tokens to every session and 1,269 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…