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 benchmark-methodologygit 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/benchmark-methodology)<a href="https://agentmods.dev/skills/gongyijie85/dsh-ecc/benchmark-methodology"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/benchmark-methodology/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/benchmark-methodology"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/benchmark-methodology.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 | $0.00072 | $0.02223 |
| Opus 5 | $0.00036 | $0.01111 |
| Sonnet 5 | $0.00014 | $0.00445 |
| Haiku 4.5 | $0.00007 | $0.00222 |
Grade A, and why
benchmark-methodology 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.
This is a copy
94% identical to benchmark-methodology — 1 line 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark Methodology
Use this skill to turn a scoped competitor set into comparable, defensible scores. Each competitor is assessed on the same nine dimensions, with explicit 1–5 rubrics, then captured in a uniform profile card. Consistency is the point: scores are only useful if the same evidence would earn the same number for any competitor.
When to Activate
- A scoped, tiered competitor set from competitive-platform-analysis is ready to score.
- Need comparable, evidence-anchored scores across competitors — not gut-feel rankings.
- Client's strategic tension (the paired axes defining their target white-space) has been established.
- Preparing to produce profile cards for assembly in competitive-report-structure.
Client positioning brief (establish first)
Before scoring, establish the client's positioning brief. It supplies:
- Strategic tension — the two axes (e.g., memorability × hireability) whose intersection marks the client's target white-space. Dimension 9 is always the client's named tension; report both poles separately, never averaged.
- Differentiator — what makes the client's moat. This informs which dimensions matter most for the client's positioning argument.
- Brand balance — the intended mix of distinct strategic emphases. Strategic recommendations must not break this balance without flagging it.
Why these dimensions
The client competes on a specific tension held across two poles, not on service breadth. The dimensions are weighted to reflect that moat. Two dimensions — the tension poles — are scored separately and never averaged together, because the client's strategic question is precisely whether a rival achieves both simultaneously.
The nine dimensions (with weights)
Weights guide synthesis emphasis, not a single blended score (avoid a false composite — see Bias controls). Sum = 100%.
- Positioning clarity & distinctiveness (18%) — Is the studio's position sharp, ownable, and instantly legible? Or generic?
- Brand voice / verbal distinctiveness (15%) — Does the copy have an ownable register, or is it interchangeable agency-speak?
- Visual identity & site craft (15%) — Quality and ownership of the visual system; site as proof-of-craft.
- Service offer & packaging (12%) — Productized and legible (named sprints/audits) vs vague. Packaging maturity.
- Evidence & credibility (12%) — Named clients, quantified outcomes, case-study depth. Proof beyond assertion.
- Enterprise-readiness / commercial maturity (10%) — Signals they can land and hold SaaS/fintech/B2B/enterprise work (process, logos, scale, contracts).
- Thought leadership / content presence (8%) — Owned POV: writing, talks, newsletters, frameworks. Depth over volume.
- Pricing transparency & engagement model (5%) — Is pricing/engagement legible? Productized vs bespoke vs opaque.
- [Client's strategic tension] (5% as a flag; score BOTH poles, report separately) — Read the tension name and axis descriptions from the client's positioning brief. Plot both; the gap is the insight. The client's target quadrant is the single most important finding: who else is already there?
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 · 192 lines · 72 tokens per session scan A f2cba14bb87f
benchmark-methodology is a skill published in the GitHub repository gongyijie85/dsh-ecc (6 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 2,223 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to benchmark-methodology, differing in 1 line, 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…
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…
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
douyin-works-crawler
A tool that retrieves basic information and recent videos from a Douyin account, using its name or Douyin ID. It can return up to 50 videos with engagement data and links.
playlet-douyin-feed
A tool that tracks popular short dramas on Douyin, a Chinese short-video platform, and creates a daily HTML report with covers, engagement data, links, topic groups, and writing observations.
playlet-xhs-feed
A daily tracker for popular short-drama posts on Xiaohongshu, a Chinese social-media platform. It groups posts by story themes and creates an HTML report with covers, interaction data, links, and writing insights.