deepseek-harness: Skill for Claude Code

.agents/skills/dsh-trim-cot-leakage/SKILL.md

dsh-trim-cot-leakage is a skill for Claude Code, Codex from deepseek-ai/deepseek-harness. It costs 109 tokens per session (1,738 once invoked), scanned A, original, MIT.

A prose-review guide for removing traces of private drafting or reasoning from published writing. It checks for unexplained session references, review notes, temporary codes, and descriptions of how the text was produced.

In plain words
What is it for?
Use it when cleaning READMEs, documentation, comments, or other project text that may expose internal editing history or draft-only references.
Why use it?
It helps documentation read as a clear statement of the current project rather than as a transcript of an editing process. It preserves useful facts by rewriting them from the reader’s point of view.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is deepseek-ai/deepseek-harness's own configuration. It tells Claude Code and Codex how to work on deepseek-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything deepseek-harness configures →

About the project

DeepSeek Harness is an open-source framework for building and running AI agents, organized so that its functionality is provided through plugins. Developers use it to launch agent workflows through a local web interface or from source, while the catalogue add-ons extend the harness as plugins.

deepseek-ai/deepseek-harness · 220,543 stars · on GitHub · deepseek.com

Reuse

Borrowing it

Nothing to install: this file belongs to deepseek-ai/deepseek-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/deepseek-ai/deepseek-harness/master/.agents/skills/dsh-trim-cot-leakage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/deepseek-ai/deepseek-harness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for dsh-trim-cot-leakage

README.md
[![agentmods](https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-trim-cot-leakage/github.svg)](https://agentmods.dev/skills/deepseek-ai/deepseek-harness/dsh-trim-cot-leakage)
Your own site
<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/dsh-trim-cot-leakage"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-trim-cot-leakage/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.

agentmods 80×15 button for dsh-trim-cot-leakage

Your own site · 80×15
<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/dsh-trim-cot-leakage"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-trim-cot-leakage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.01738
Opus 5 $0.00055 $0.00869
Sonnet 5 $0.00022 $0.00348
Haiku 4.5 $0.00011 $0.00174

Measured 12d ago against content hash d81b60699eec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dsh-trim-cot-leakage 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/dsh-trim-cot-leakage/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trimming Chain-of-Thought Leakage

Chain-of-thought leakage is prose whose vantage is the authoring session rather than the repository: it cites artifacts only that session could see, narrates the change instead of the state, or argues with a reviewer who has left. The fix is never deletion alone when a passage carries factual clauses — restate each so it stands at HEAD, then delete the transcript around it; a passage carrying none (an audit code, control-flow narration) is deleted outright. REQUIRED BACKGROUND: dsh-prose-standard owns the complete-proposition rule this skill applies; the committed-artifact-citations note owns the citation rule's rationale. It is guidance, not a script.

The one test

For every suspect passage ask: could a reader at HEAD, with no access to any session transcript, PR thread, or uncommitted draft, resolve every reference and verify every claim? If no, restate the surviving facts from the repository's vantage and delete the rest. If yes, it is not leakage, however historical it sounds — but resolvability only clears this skill's bar: on current-state surfaces (READMEs, docs, JSDoc) a resolvable change story is still change narration, and class 3 routes it to its sanctioned home.

Taxonomy

  1. Dead design-session citations(decision 7), (audit C2), design §4.7, plan §1.4, phase labels (T4, W3, P-I), "the design ledger", "(B ruling)". If the decision has a committed owner, cite it by name and path; otherwise delete the citation and restate its factual clause to stand alone.
  2. Stack and PR vantage — "a later PR in this stack", "this PR adds", "the previous commit". State the shipped mechanism or the extension point; deferred work moves to a TODO marker or an issue reference.
  3. Change narration and version stamps — "used to", "no longer", "the old X", and indexical stamps ("v1", "this cut", "today", "now" contrasting with a past state). State the present behavior; a fixed regression becomes a present-tense counterfactual ("without X, Y happens"), never repo history ("used to Y").
  4. Review choreography — "Rejected in review:", "the reviewer confirmed", draft ordinals ("v5 of this note"), round attributions. Keep the surviving decision and rationale as plain fact; delete who said it when.
  5. Reviewer-addressed justification — "the cast is safe — it simply…", "this is correct because…". A comment arguing its own correctness addresses a reviewer, not a maintainer. State the invariant that makes the code safe, or delete the comment if the code shows it.
  6. Restatement and derivation transcripts — control-flow narration ("first we X, then we Y"), test walkthroughs, proofs of obvious branches. Delete; keep only a non-obvious contract or invariant.
  7. Hedges and planning residue — "probably fine for now", "should be enough", deferrals with no marker. Promote to TODO/FIXME or restate as the actual bound; delete the hedge.
  8. Authoring-language slips — untranslated working-language fragments (端, 设计稿, ---- 私有 ---- separators) in prose whose language is otherwise English, or the reverse in a zh counterpart. Translate or delete.

Read the full file on GitHub · 46 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 46 lines · 109 tokens per session scan A d81b60699eec

Subscribe to this mod's changes

dsh-trim-cot-leakage is a skill published in the GitHub repository deepseek-ai/deepseek-harness (220,543 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 1,738 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

dsh-web-community-plugin-developer

Develop a DSH community plugin and register it in the dsh-web Community Plugins index — author the plugin in the contributor's own repository following the official cordis bundle standard, add its entry to packages/dsh-community-plugins/community.json, regenerate the index with scripts/community-index, rebuild and…

zhu1090093659/dsh-web · 123 tokens

dsh-web-skin-developer

Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…

zhu1090093659/dsh-web · 120 tokens

dsh-web-pet-developer

Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…

zhu1090093659/dsh-web · 162 tokens

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…

shengsheng90/DSH-taskboard · 88 tokens

industry-research-method

A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.

PerryLink/dsh-industry-research · 96 tokens

company-research-method

A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.

PerryLink/dsh-industry-research · 83 tokens