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 agentmods add skills/cintia09/codenook/device-detectnpx skills add cintia09/CodeNook --skill device-detectgit clone --depth 1 https://github.com/cintia09/CodeNookWhat 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 | $0.00003 | $0.00775 |
| Opus 5 | $0.00002 | $0.00387 |
| Sonnet 5 | $0.00001 | $0.00155 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
device-detect 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
device-detect — plugin-shipped skill (development plugin)
Role
Enumerate every file / directory under <target-dir> that might be
an execution-environment hint, classify each by a generic bucket, and
emit a JSON envelope. The skill is deliberately liberal — it does
not decide what kind of device or simulator the target is, only what
markers exist. Classification is the test-planner's job, and it does
that by:
- Searching workspace memory for a matching environment record:
<codenook> knowledge search "test-environment target=<basename>". - If memory is silent, asking the user to identify the environment.
CLI
detect.py --target-dir <dir> [--json]
Detection (generic markers, no device-type hard-coding)
Marker pattern under <target> |
Bucket |
|---|---|
pyproject.toml / setup.py / pytest.ini |
local-python |
package.json |
local-node |
go.mod |
local-go |
Any .codenook-test-env* / .test-env* file |
recorded-env |
Any dot-config file matching *.cfg / *.toml / *.yaml at the root that does not match a known software runner |
unknown-config |
Any scripts/run-*-tests.sh |
custom-runner |
| (none of the above) | unknown |
The buckets are intentionally generic (local-*, recorded-env,
unknown-config, custom-runner, unknown) — the specific device
or simulator type (ADB / QEMU / SSH-into-board / JTAG / network
fixture / …) is never decided here. That decision belongs to the
calling role + memory + user.
JSON envelope (--json)
{
"target": "src/",
"buckets": ["local-python", "custom-runner"],
"primary": "local-python",
"markers": {
"local-python": ["pyproject.toml"],
"custom-runner": ["scripts/run-board-tests.sh"]
},
"memory_search_hint": "test-environment target=foo"
}
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.
- 2d ago First seen · 84 lines · 3 tokens per session scan A f4e7377d333a
device-detect is a skill published in the GitHub repository cintia09/CodeNook (5 stars, last pushed 3mo ago), licensed MIT. It adds 3 tokens to every session and 775 once invoked, about $0.0000 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
create-skill
Create new Datus skills from scratch. Use when users want to build a new skill, scaffold a skill directory, or capture a workflow as a reusable skill. Trigger phrases include "create a skill", "make a skill for", "turn this into a skill", "new skill".
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.