Borrowing it
Nothing to install: this file belongs to ashishpatill/tell-proof. 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/ashishpatill/tell-proof/master/.cursor/skills/tell-detector-authoring/SKILL.mdgit clone --depth 1 https://github.com/ashishpatill/tell-proofWrote 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/ashishpatill/tell-proof/tell-detector-authoring)<a href="https://agentmods.dev/skills/ashishpatill/tell-proof/tell-detector-authoring"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-detector-authoring/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/ashishpatill/tell-proof/tell-detector-authoring"><img src="https://agentmods.dev/badge/skills/ashishpatill/tell-proof/tell-detector-authoring.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 | $0.00100 | $0.00530 |
| Opus 5 | $0.00050 | $0.00265 |
| Sonnet 5 | $0.00020 | $0.00106 |
| Haiku 4.5 | $0.00010 | $0.00053 |
Grade A, and why
tell-detector-authoring 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 7d 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.
What it actually says
Tell detector authoring
Scope
packages/schema— add or extendTellDetector/DriftDetectorenums andFindingfields firstpackages/core/src/detectors/index.ts— all 14 detectors live here unless a real split is neededpackages/core/src/__tests__/detectors.test.ts— golden assertions against committed capture JSON
Rules
- No LLM, API, or model calls in core
- Detectors are pure:
(fingerprint: DesignFingerprint, capture: CapturePayload) => Finding[] - Emit deterministic
factsandevidence; taste layer assigns final verdicts - Use
Finding.parse(...)at emit time - Set
verdictHintmechanically; taste may override tointentional
Workflow
- Read threshold spec in
BUILD.md§5.3–5.4 - If schema changes are needed, edit
@tell/schemafirst and rebuild - Add detector logic in
detectFindings - Update golden test expectations in
detectors.test.ts - If fixture UI must change to plant the finding, coordinate with
tell-demo-fixtureskill - Run
pnpm test
Finding shape
Finding.parse({
id: "tell-example",
family: "tell", // or "drift"
detector: "SystemFontTell",
verdictHint: "generic",
severity: "high",
facts: { /* measured numbers only */ },
evidence: [{ kind: "computed", label: "...", value: "..." }],
});
DoD
- Detector is deterministic and reproducible on
fixtures/reports/capture.json - Golden test passes
- No invented facts that taste cannot validate
Related
- Rules:
.cursor/rules/tell-core-engine.mdc - Agent:
.cursor/agents/core-engineer.md - Methodology:
docs/05_GENERICNESS_METHODOLOGY.md
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.
- 7d ago First seen · 56 lines · 100 tokens per session scan A 70480091dc79
tell-detector-authoring is a skill published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 15d ago), licensed MIT. It adds 100 tokens to every session and 530 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
testing
To write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.
Add executable smoke tests for shell scripts and CLIs before refactors ship
Use Bats-core when an agent needs to turn fragile shell scripts or command-line workflows into something it can verify repeatedly after edits. The agent writes focused Bash tests for success paths, failure paths, and output contracts, then runs them locally or in CI before a refactor, release, or incident fix goes out.
test-writer
Writes tests for code that already exists: behaviour over implementation, arrange-act-assert structure, mocks only at real boundaries, and no time- or order-dependent flakiness. Use when asked to add tests, close a coverage gap on a function, component, or endpoint, or write a regression test for a bug just fixed. Not…
testing-patterns
Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle.
dev-testing
A testing guide that defines when to use unit, integration, API, and end-to-end tests. Unit tests check small pieces of code, while end-to-end tests check a full user flow.