Borrowing it
Nothing to install: this file belongs to rani700/careerpilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rani700/careerpilot/main/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/rani700/careerpilotWrote 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/rani700/careerpilot/verify)<a href="https://agentmods.dev/skills/rani700/careerpilot/verify"><img src="https://agentmods.dev/badge/skills/rani700/careerpilot/verify/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/rani700/careerpilot/verify"><img src="https://agentmods.dev/badge/skills/rani700/careerpilot/verify.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 | $0.00035 | $0.00948 |
| Opus 5.5 | $0.00014 | $0.00379 |
| Sonnet 5.5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
verify 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying CareerPilot
The surface is the MCP protocol over stdio — always test by spawning the real server process and speaking MCP to it, never by importing server functions.
Handle
uv sync # install (uses .venv)
uv run careerpilot # server on stdio (blocks; speaks JSON-RPC)
Quick handshake probe (no client code needed):
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"probe","version":"0"}}}' \
| uv run careerpilot 2>/dev/null | head -c 400
Full E2E drive
Write a Python client using mcp.client.stdio.stdio_client + ClientSession with:
StdioServerParameters(command="uv", args=["run", "careerpilot"], cwd=<repo>, env={**get_default_environment(), "CAREERPILOT_DB": <tempfile>})— the env override keeps the user's real DB (~/.careerpilot/) untouched.envREPLACES the environment, so mergeget_default_environment()or uv won't find PATH/HOME.sampling_callbackreturning a cannedCreateMessageResult→ exercisesscore_job_fitelicitation_callbackreturningElicitResult(action="accept", content={"confirm": True})(and a decline case) → exercisesdelete_applicationlist_roots_callbackpointing at a temp dir containing a*resume*.md→ exercisesfind_resumemessage_handlercollectingServerNotifications; aftersession.subscribe_resource("careerpilot://pipeline"), any mutating tool must produce aResourceUpdatedNotification(allow ~0.3s).
Flows worth driving every time: search (live network) → save_job with external_id →
track → update → subscribe+mutate → read pipeline + careerpilot://applications/{id} →
prompt with resume in context → decline-then-accept delete.
Stage 2-4 surfaces
- Watches/poller (stage 2):
uv run python tests/stage2_watches_test.py— seeds a watch directly in the temp DB (no baseline), setsCAREERPILOT_POLL_SECONDS=2, and asserts the background poller pushesresources/updatedwith no tool call in flight. - HTTP + auth (stage 3):
uv run python tests/stage3_http_test.py— spawnscareerpilot --httpwithCAREERPILOT_TOKEN, asserts 401 (no/wrong token, withWWW-Authenticate) and a full session viastreamablehttp_clientwith the token. - Host (stage 4):
uv run careerpilot-chat --listneeds no API key and must show 14 tools / 4 resources / 2 templates / 3 prompts. The chat loop (host.chat_turn) can be driven with a scripted fake LLM against the real server over stdio; a live chat turn needsANTHROPIC_API_KEY.
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 · 72 lines · 35 tokens per session scan A 8f0607e797eb
verify is a skill published in the GitHub repository rani700/careerpilot (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 948 once invoked, about $0.0001 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.