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 implicit-labs/autosymph --skill verify-preflightgit clone --depth 1 https://github.com/implicit-labs/autosymphWrote 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/implicit-labs/autosymph/verify-preflight)<a href="https://agentmods.dev/skills/implicit-labs/autosymph/verify-preflight"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/verify-preflight/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/implicit-labs/autosymph/verify-preflight"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/verify-preflight.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 | $0.00077 | $0.01326 |
| Opus 5.5 | $0.00031 | $0.00530 |
| Sonnet 5.5 | $0.00015 | $0.00265 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
verify-preflight 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 2mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-preflight
Fast-fail probes for verify agent infrastructure. Run this FIRST. If it returns
exit 2, do NOT enter test classification or execution — emit the BLOCKED table
the script printed and signal fail.
When to Use
Always, at the very start of any verify run, BEFORE Phase 1 (Load Context).
This skill exists because verify agents waste 5–10 minutes per run discovering that idb is broken or auth.md is missing by trying ui_tap or launching the sim and watching it fail repeatedly. A 10-second deterministic probe replaces the trial-and-error.
The Script
${AUTOSYMPH_SKILLS_DIR:-$HOME/.autosymph/skills}/verify-preflight/scripts/preflight.sh \
--workspace "$WORKSPACE" \
[--ios] [--web] [--auth-gated]
Pass the flags that match the test plan. If the test plan has any iOS items,
pass --ios. If any web items, --web. If the feature under test is
auth-gated (you need to log in to reach it), pass --auth-gated.
The script writes a single JSON line to stdout, then a markdown table:
{"status":"blocked","blocked_categories":["ios"],"probes":{"idb":{"result":"broken","detail":"python3 cannot import pyexpat: ..."}}}
## Verify Preflight
| Probe | Result | Detail |
|-------|--------|--------|
| idb | BLOCK (broken) | python3 cannot import pyexpat: ... |
| sim | PASS (ok) | simctl available |
**Blocked categories:** ios
Mark every test item in the blocked categories as BLOCKED with the matching probe detail. Signal verify result `fail` with reason `preflight: ios`. Do not enter Phase 1+.
Exit Codes
| Code | Meaning | Agent action |
|---|---|---|
| 0 | All probes passed | Continue to Phase 1 |
| 2 | At least one blocker | Emit BLOCKED table for affected items, signal fail |
| 1 | Script error (bad args, missing python3) | Treat as soft failure, continue but log warning |
What the Probes Check
| Probe | What it verifies | Bounded by |
|---|---|---|
auth_md |
.autosymph/verify/auth.md exists and is non-empty |
none (file check) |
idb |
python3 -c "import pyexpat" succeeds AND idb --help works |
5s timeout each |
sim |
xcrun simctl list devices booted returns 0 |
5s timeout |
playwright |
npx --no-install playwright --version succeeds |
8s timeout |
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.
- 2mo ago First seen · 128 lines · 77 tokens per session scan A 757095c4507e
verify-preflight is a skill published in the GitHub repository implicit-labs/autosymph (5 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,326 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 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.