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 jleechanorg/agent-orchestrator-ts --skill technique-routergit clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-tsWrote 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/jleechanorg/agent-orchestrator-ts/technique-router)<a href="https://agentmods.dev/skills/jleechanorg/agent-orchestrator-ts/technique-router"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/technique-router/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/jleechanorg/agent-orchestrator-ts/technique-router"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/technique-router.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 | $0.00030 | $0.00607 |
| Opus 5.5 | $0.00012 | $0.00243 |
| Sonnet 5.5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
technique-router 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 9d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
technique-router — ZFC-Compliant PR Type Classification Skill
Purpose
Classifies a GitHub issue/PR description into a PR-type category, then recommends the appropriate autor technique. This is classification-only until routing is wired: classifyPrType() returns PR-type metadata, but technique resolution still happens separately through prompt/config defaults. All classification is delegated to the model API — no heuristic scoring, keyword matching, or hardcoded routing tables.
PR Types
| Type | Description |
|---|---|
state-bool |
Widening boolean semantics (int 1/0, string '1'/'0' as valid True/False) |
data-norm |
Normalizing key names and numeric formats (xp→xp_gained, NaN handling) |
ci-workflow |
GitHub Actions workflow changes (YAML scripting, gate logic) |
typeddict-schema |
TypedDict + validation for previously untyped data structures |
large-arch-refactor |
Module extraction, moving functions between files |
unknown |
Cannot determine from the description |
Technique Selection (Autor Research — Phase 10)
All 9 autor techniques converge within rubric noise (~80-85 confidence-interval overlap). SR-prtype is the safe default for all PR types. No per-type routing is statistically justified.
| Technique | Description | When to use |
|---|---|---|
SR-prtype |
Self-Refine with PR-type classification | Safe default for all types |
SR-fewshot |
Self-Refine with single prior PR exemplar | When a highly similar prior PR exists |
SR |
Basic 3-round self-refine | Fallback |
ET |
Extended chain-of-thought reasoning | Complex architectural decisions |
PRM |
Process Reward Model (score each step) | Debugging, multi-step reasoning |
Usage
/technique-router <issue-title> <issue-body-or-url>
ZFC Compliance
This skill does NOT:
- Match keywords like "fix", "bug", "refactor" to determine type
- Use regex or substring checks for intent detection
- Apply hardcoded scoring weights
- Use if/else chains that guess intent from text
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.
- 9d ago First seen · 57 lines · 30 tokens per session scan A 4094747ca36b
technique-router is a skill published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 607 once invoked, about $0.0001 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 2026-10-02.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…