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 tacoda/keystone-mcp --skill keystone-sensor-runnergit clone --depth 1 https://github.com/tacoda/keystone-mcpWrote 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/tacoda/keystone-mcp/keystone-sensor-runner)<a href="https://agentmods.dev/skills/tacoda/keystone-mcp/keystone-sensor-runner"><img src="https://agentmods.dev/badge/skills/tacoda/keystone-mcp/keystone-sensor-runner.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 | $0.00013 | $0.00550 |
| Opus 5 | $0.00006 | $0.00275 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
keystone-sensor-runner 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
keystone-sensor-runner
Single entry point for the verify phase: enumerate sensors, run each in its correct mode, report aggregate PASS/FAIL.
Sensors live in two ports:
sensors/<name>.mddeclares each sensor (kind, intent, blocking status).scripts/<name>.shimplements computational sensors. Exit 0 = pass.prompts/<name>.mdimplements inferential sensors. Agent reads the prompt and reports PASS or FAIL with cited findings.
Convention: a sensor named <x> is computational if and only if
scripts/<x>.sh exists. If prompts/<x>.md exists instead, the
sensor is inferential. Both → ambiguous (warn + prefer the script).
When to use
The verify phase of the task playbook (or any other flow that gates
on sensor outcomes — release, doctor, audit).
Activities
- Enumerate. Read
keystone://harness/statusto list everything undersensors/. For each, decide mode by checking which implementation file exists. - Run computational sensors. Each
scripts/<name>.shruns via Bash. Exit 0 = pass; non-zero = fail. Capture stdout + stderr. - Run inferential sensors. For each
prompts/<name>.md:- Read the prompt body.
- Perform the reasoning task it describes against the current diff (or scoped region).
- Report PASS or FAIL with cited findings (file:line refs, no invented evidence).
- Aggregate. Build one report: Sensor Mode Status Cause (on fail) -------- ------------- ------ --------------- lint computational PASS code-review inferential FAIL "...specific finding..."
- Halt on any FAIL. Surface to the user. Do not advance the playbook past verify.
Output
A unified PASS/FAIL report. The runner does not modify the diff or the harness; it only observes and reports.
Iron laws
- Sensors are blocking. A FAIL halts the workflow.
- No
--no-verifyto bypass a sensor. - No invented evidence in inferential findings — cite real diff/file lines.
- No completion claims without a fresh run. Stale verification evidence is not evidence.
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 · 61 lines · 13 tokens per session scan A c8e97ff38465
keystone-sensor-runner is a skill published in the GitHub repository tacoda/keystone-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 550 once invoked, about $0.0001 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.