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 gongyijie85/dsh-ecc --skill orch-refine-codegit clone --depth 1 https://github.com/gongyijie85/dsh-eccWrote 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/gongyijie85/dsh-ecc/orch-refine-code)<a href="https://agentmods.dev/skills/gongyijie85/dsh-ecc/orch-refine-code"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/orch-refine-code/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/gongyijie85/dsh-ecc/orch-refine-code"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/orch-refine-code.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 | $0.00047 | $0.00451 |
| Opus 5 | $0.00023 | $0.00226 |
| Sonnet 5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
orch-refine-code 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.
This is a copy
100% identical to orch-refine-code — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
orch-refine-code
Actor · action · target: orch · refine · code. Thin wrapper over the shared
engine in orch-pipeline.
When to Use
- Same behavior, better structure: extract modules, remove duplication, kill dead code, reduce nesting, rename for clarity.
- Distinguish from siblings: if behavior is meant to change at all, this is the
wrong skill (
orch-change-feature/orch-fix-defect).
Operation settings
- Default size floor: standard — restructures touch multiple files.
- Phase mask: 0 → 2 (plan the restructure) → 4 (keep green) → 5 → 6. No new behavior tests are written — the existing suite is the safety net.
- First move (phase 4): confirm the relevant tests exist and are green before touching code; if coverage is thin, add characterization tests first. Then restructure in small steps, re-running tests after each.
How It Works
- Run the
orch-pipelineengine with the settings above. - For dead-code / duplication sweeps, delegate to the
refactor-cleaneragent (it runs knip / depcheck / ts-prune and removes safely). - Stop at Gate 1 (restructure plan) and Gate 2 (pre-commit).
- Commit as
refactor:— the diff must be behavior-neutral.
Example
orch-refine-code: extract the NWS HTTP client out of poller.py
→ confirm tests green → plan extraction [GATE 1: approve]
→ move in small steps, tests green throughout → code-review
→ commit refactor: [GATE 2: confirm]
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 · 45 lines · 47 tokens per session scan A 5f0f468ffa4e
orch-refine-code is a skill published in the GitHub repository gongyijie85/dsh-ecc (7 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 451 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to orch-refine-code, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
delivery-proof
Delivery proof and the doublecheck report. Use when the work is done and the delivery must be proven — consolidate the spec, test timeline, review verdicts, and verification checks into a doublecheckreport, and only then claim completion.
delivery-review
Adversarial self-review before delivery. Use once the implementation reaches green and before you declare the work done — assume the delivery fails its own spec, hunt for the strongest supportable objections, answer them, and re-review after fixes.
red-green-tdd
Red/green test discipline for implementation work. Use once a doublecheck spec is on record and implementation is about to start — write a test that fails for the missing behavior, run it to see it fail (red), make the change, run again to see it pass (green).
code2skill-review-source
A read-only review skill for checking whether a Code2Skill-generated result matches the source code it was authorized to use. It examines request handling, tool handoffs, transformations, authentication, and attachments.
code2skill-review-flow
A read-only reviewer for the main user flows in a package generated by Code2Skill. It checks whether representative paths are basically usable, without proving that every source-code detail is included.