Borrowing it
Nothing to install: this file belongs to rakovi4/continue-framework. 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/rakovi4/continue-framework/main/.claude/skills/test-spec/SKILL.mdgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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/rakovi4/continue-framework/test-spec)<a href="https://agentmods.dev/skills/rakovi4/continue-framework/test-spec"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/test-spec/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/rakovi4/continue-framework/test-spec"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/test-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.03022 |
| Opus 5.5 | $0.00017 | $0.01209 |
| Sonnet 5.5 | $0.00008 | $0.00604 |
| Haiku 4.5 | $0.00004 | $0.00302 |
Grade A, and why
test-spec 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 1mo 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Test Specifications
Generate BDD-style test specifications for a story in 6 categories — one file per
category under tests/. The drafted scenarios are then split by consequence of
failure into three tiers (.claude/templates/spec/tier-ladder.md): Tiers 1 and 2
are implemented in that order, Tier 3 is recorded in tests/tier3/ and never built.
Usage
/test-spec "Story name"
/test-spec 5 # By MVP story number
/test-spec # Interactive selection
Workflow
Phase 1: Context & Story Selection
Parse input first — by name ("Login/Logout"), by number (5), or interactive (list and ask) — since the reads below are scoped to the resolved story and the areas it touches.
Read before generating: ProductSpecification/BriefProductDescription.md, ProductSpecification/stories.md, ProductSpecification/ExpectedLoad.md, and the target story's folder: mockups/, its spec *.md, endpoints.md, interview.md. Resolve that folder stories/NN-story-name/ first, then stories/done/NN-story-name/ (.claude/rules/workflow.md, "Resolving a story folder") — these reads tolerate absence, so an unresolved archived folder is indistinguishable from a story that has no interview, and generation proceeds from the spec alone.
For what the product already does in the areas this story touches — so a drafted scenario neither re-specifies shipped behavior nor contradicts it — read the acceptance tests of those areas: test class names, scenario descriptions, Statements. Never sweep the other story folders to reconstruct it (.claude/rules/workflow.md, "Where the Current State Lives"). Only enabled tests count as shipped — one still carrying its disable/skip marker is a pending increment, not shipped behavior. Where the suite is silent about an area, read that area's production code — silence is not evidence of absence. In a repo with no acceptance suite yet, say so explicitly and fall back to the story folders. Open an earlier story's folder only for a named precedent: the decision behind a rule this story extends — under stories/ or stories/done/, a closed story being the usual home of a settled rule (.claude/rules/workflow.md, "Resolving a story folder").
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.
- 1mo ago Changed · +8 lines c0461bcdcc3c
- 1mo ago Changed · -35 lines 104d08f25cf9
- 1mo ago Changed · +6 lines 5983c3eeec49
- 2mo ago First seen · 194 lines · 42 tokens per session scan A 8ee06a53f327
test-spec is a skill published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 42 tokens to every session and 3,022 once invoked, about $0.0002 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 2026-08-30.
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".
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.
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.