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 Metalnib/dotnet-episteme-skills --skill dotnet-techne-qa-pipelinegit clone --depth 1 https://github.com/Metalnib/dotnet-episteme-skillsWrote 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/metalnib/dotnet-episteme-skills/dotnet-techne-qa-pipeline)<a href="https://agentmods.dev/skills/metalnib/dotnet-episteme-skills/dotnet-techne-qa-pipeline"><img src="https://agentmods.dev/badge/skills/metalnib/dotnet-episteme-skills/dotnet-techne-qa-pipeline/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/metalnib/dotnet-episteme-skills/dotnet-techne-qa-pipeline"><img src="https://agentmods.dev/badge/skills/metalnib/dotnet-episteme-skills/dotnet-techne-qa-pipeline.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 | $0.00086 | $0.01541 |
| Opus 5 | $0.00043 | $0.00771 |
| Sonnet 5 | $0.00017 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
dotnet-techne-qa-pipeline 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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story QA pipeline (multi-agent)
You are the orchestrator. Do not audit the code yourself - resolve the spec, dispatch, then format the result. Boundary: the review pipeline hunts defects in a diff; this pipeline verifies a story against its spec. Same branch, different question.
Paths below are relative to this skill's base directory. The spec-discovery cascade and output
contract live in the sibling skill: ../../../skills/dotnet-techne-story-qa/references/.
Step 0 - Check the budget, then the roles
A spec-mode run spends four agent turns - three QA lanes plus the maintainer (three turns in
no-spec mode). Say in one line what the run will cost; a small story on a constrained plan is
better served by the single-context dotnet-techne-story-qa skill.
List your available agent roles. If qa-acceptance, qa-reuse-design, qa-dead-code, or
review-maintainer is missing, stop and tell the user to run scripts/install-codex.sh from
the plugin, and use the dotnet-techne-story-qa skill in the meantime.
Step 1 - Resolve target
The story diff: the current branch vs its merge-base with the default branch, unless the user names a branch, ticket, or base. Slug the story (ticket key if known, else branch name). Nothing to diff - halt and say so.
Step 2 - Resolve the spec (cascade)
Follow ../../../skills/dotnet-techne-story-qa/references/spec-discovery.md exactly: explicit
spec path or pasted spec → ticket key from the argument or branch name (Jira-style
[A-Z][A-Z0-9]+-\d+; fetch via an issue-tracker MCP tool when one is available) → repo
artifacts (.episteme/DESIGN-*.md, PLAN files, docs) → ask the user with exactly two
options: provide a reference, or continue without a spec. Never infer no-spec mode from a
missing path.
Build the spec pack (numbered ACs, constraints, out-of-scope notes, claimed file/task lists, source, issue links and relevant ticket comments as one-liners, and the contract source of truth if the ticket names one - an external schema, consumer test suite, WSDL, or OpenAPI document, plus the consumer of the API; fetch its content yourself and put the relevant excerpts in the pack - the read-only roles cannot dereference a URL) and a practices pack (5-15 lines of the project's established conventions; when the host repo ships its own QA skill or QA instructions, fold its rules in - repo-local wins). Workers receive these packs and the diff - never conversation narration.
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.
- 12d ago First seen · 100 lines · 86 tokens per session scan A e1f4bdd20d44
dotnet-techne-qa-pipeline is a skill published in the GitHub repository Metalnib/dotnet-episteme-skills (12 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 1,541 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
improve-code-quality
Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.
prompt-caching-patterns
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cachecontrol, cache breakpoint, cache TTL, hit rate.
code-review
Review .NET changes for bugs, regressions, architectural drift, missing tests, incorrect async or disposal behavior, and platform-specific pitfalls before you approve or merge them. USE FOR: reviewing a pull request or patch in a .NET repository; checking for behavioral regressions, API misuse, or missing tests…
test-verification
Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.
dotnet-best-practices
Ensure .NET/C# code follows maintainable, modern best practices. Use when reviewing or improving C# code, solution structure, async patterns, dependency injection, or testability.