Borrowing it
Nothing to install: this file belongs to e7nd7r/gnapsis. 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/e7nd7r/gnapsis/main/.claude/skills/smoke-test/SKILL.mdgit clone --depth 1 https://github.com/e7nd7r/gnapsisWrote 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/e7nd7r/gnapsis/smoke-test)<a href="https://agentmods.dev/skills/e7nd7r/gnapsis/smoke-test"><img src="https://agentmods.dev/badge/skills/e7nd7r/gnapsis/smoke-test/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/e7nd7r/gnapsis/smoke-test"><img src="https://agentmods.dev/badge/skills/e7nd7r/gnapsis/smoke-test.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 | $0.00024 | $0.05004 |
| Opus 5.5 | $0.00010 | $0.02002 |
| Sonnet 5.5 | $0.00005 | $0.01001 |
| Haiku 4.5 | $0.00002 | $0.00500 |
Grade A, and why
smoke-test 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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gnapsis Smoke Test
Run through every gnapsis MCP tool to verify the system is functional. This skill exercises the full feature set: project setup, taxonomy, entity CRUD, references, search, subgraph queries, document analysis, validation, and multi-source support.
Prerequisites
- Database must be running:
just db-up - gnapsis must be installed:
cargo install --path . - MCP server must be connected:
/mcp
Test Procedure
Run each phase sequentially. If any step fails, jump to Phase 10 (Cleanup) to restore the original config before reporting the failure. Track entity IDs, reference IDs, and category IDs created during the test for cleanup.
Phase 0: Config Isolation
The smoke test uses a separate project name (gnapsis_smoke_test) so it gets its own
graph and does not interfere with the real project data.
0.1 Backup the real config:
cp .gnapsis.toml .gnapsis.toml.bak
0.2 Overwrite .gnapsis.toml with the smoke test config:
# Force local database — overrides global ~/.config/gnapsis/config.toml
[postgres]
uri = "postgresql://postgres:postgres@localhost:5432/gnapsis_dev"
[embedding]
provider = "fastembed"
model = "BAAI/bge-small-en-v1.5"
dimensions = 384
[project]
name = "smoke_test"
[[project.sources]]
id = "default"
path = "<absolute path to this repo>"
[[project.sources]]
id = "vault"
path = "<absolute path to vault source from the backup>"
Copy the source paths from the backup file. The key differences are:
[postgres]and[embedding]force the local Docker database (overrides global config)name = "smoke_test"creates graphgnapsis_smoke_testinstead ofgnapsis_gnapsis
0.3 Reconnect the MCP server so it picks up the new config: /mcp
Phase 1: Database Reset & Init
1.1 Drop the smoke test graph so init starts fresh:
just db-reset
just db-up
Wait for the database to be ready before proceeding.
1.2 Run init_project (force: true) and verify:
- Response includes
db_versionandgraph_version applied_db_migrationsis non-emptyapplied_graph_migrationsis non-emptywas_initializedis false (fresh graph)
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 · 510 lines · 24 tokens per session scan A 090ac7ff2b64
smoke-test is a skill published in the GitHub repository e7nd7r/gnapsis (5 stars, last pushed 8mo ago), licensed MIT. It adds 24 tokens to every session and 5,004 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.