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-refactor-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-refactor-pipeline)<a href="https://agentmods.dev/skills/metalnib/dotnet-episteme-skills/dotnet-techne-refactor-pipeline"><img src="https://agentmods.dev/badge/skills/metalnib/dotnet-episteme-skills/dotnet-techne-refactor-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-refactor-pipeline"><img src="https://agentmods.dev/badge/skills/metalnib/dotnet-episteme-skills/dotnet-techne-refactor-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 | $0.00113 | $0.01828 |
| Opus 5 | $0.00056 | $0.00914 |
| Sonnet 5 | $0.00023 | $0.00366 |
| Haiku 4.5 | $0.00011 | $0.00183 |
Grade A, and why
dotnet-techne-refactor-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 3d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring/design loop (multi-agent)
You are the orchestrator. Do not enumerate or trace code yourself - dispatch session-blind workers, persist their artifacts, and hold the gates. No code is written or edited until the design is approved at the Phase D gate.
The roles: refactor-cartographer, refactor-tracer, refactor-surveyor (lighter mode),
refactor-conformance-auditor. List your available agent roles; if they are missing, tell the
user to run scripts/install-codex.sh from the plugin, then either stop or (with the user's
consent) run the phases yourself in this context.
Step 0 - Resolve target and state
- Target: a ticket id or an area description. Slug it (e.g.
yb-1234). - State file:
.episteme/DESIGN-<slug>.mdat the repository root (create.episteme/if missing). Codex has no reload hook: re-read the file at the start of every session. - If it exists, route on its frontmatter - the file is the source of truth, never
conversation memory:
status: done→ nothing to resume;status: blocked→ restate the blocker and ask;status: awaiting-approval→ re-present the design at the Phase D gate;status: active→ resume at the phase inphase:. - If not, create it with frontmatter (
target,sources- where the request came from,phase: R,status: active,design_revision: 0) and sectionsWhy,References,Map,Traces,Probes,Design (approved),Decision log,Deferred,Todo,Review findings. Keep the frontmatter current and flush worker artifacts to the file the moment they return.Decision logandDeferredare append-only. - Fill
WhyandReferencesbefore Phase R, while the request is still fresh. They are the only sections a later reader cannot reconstruct from the code, and atargetline is not a problem statement.Whyis prose, not a list: the defect or goal in the reader's terms, what triggered the loop, why it is worth doing now rather than later, and what breaks if nothing changes. A loop that cannot state its problem in a paragraph should not be spending a worker fan-out on a map.Referencesis a provenance table: ticket and sibling ticket ids, the review or PR threads, prior QA or design files, the contract/spec source, vendor docs or live schema fetched, probe artifacts, and the host-repo rule sections applied. Cite them as ids and paths, not as bare claims - "the reviewer asked" is unusable six weeks later. Both are stable: revise them only when the problem itself changes, and never to make the design that emerged look like the one that was intended. - Invariant pack: extract the 5-15 lines of project-specific design invariants relevant to the target (CLAUDE.md sections, architecture docs). Workers receive this pack and artifact data only - never conversation narration; their blindness to the session is the anti-anchoring mechanism.
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.
- 3d ago Changed · +13 lines dd249ea444d2
- 12d ago First seen · 103 lines · 113 tokens per session scan A 086ef13a718c
dotnet-techne-refactor-pipeline is a skill published in the GitHub repository Metalnib/dotnet-episteme-skills (12 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 1,828 once invoked, about $0.0006 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
unused-code-audit
A code-audit skill for proving whether files, exports, functions, components, types, or helpers have real users before removal.
predict
Analyzes diffs for regression risk and blast radius, generates risk-scored impact report. Triggers: PR review, code change risk, breaking change, blast radius, regression check.
squid-architecture-review
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.
analyze
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report, hotspot scan, code analysis, architecture signal.
time-bomb-radar
Finds deferred operations that crash on aged data -- code that passes every test but breaks weeks or months after release. Covers cascade deletes, cache expiry, trial paths, background accumulation, date-threshold transitions, and scheduled side effects. Triggers: "time bomb", "time-bomb", "/time-bomb-radar", "aged…
radar-suite-axis-classification
Shared axis classification framework for all radar-suite skills. Every finding must be classified as axis1 (bug), axis2 (scatter), or axis3 (dead/smelly) before emission, with mandatory coaching fields and file:line citations to existing patterns in the audited codebase. Triggers: invoked by every radar before…