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 agentmods add skills/sungurerdim/dev-skills/ds-benchmarknpx skills add sungurerdim/dev-skills --skill ds-benchmarkgit clone --depth 1 https://github.com/sungurerdim/dev-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/sungurerdim/dev-skills/ds-benchmark)<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-benchmark"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-benchmark.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.04241 |
| Opus 5 | $0.00024 | $0.02121 |
| Sonnet 5 | $0.00010 | $0.00848 |
| Haiku 4.5 | $0.00005 | $0.00424 |
Grade A, and why
ds-benchmark 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 2d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ds-benchmark
Teams drift toward internal tastes — architecture that made sense to the original author doesn't match where the problem space has landed. Without an explicit external benchmark, the project's "ideal" is whatever the last contributor felt.
Ideal-vs-Current Benchmark — research 5–10 comparable projects, synthesize the ideal architecture, produce a dimension-by-dimension gap table, and let the user decide which gaps to close.
Completion Evidence — applies to every phase: Report
done/OKonly with the machine-checkable evidence the gates name — the exact command run and its observed output (orfile:linediff). Missing evidence → reportINCOMPLETEplus what is missing. Self-assessment is never evidence. (This band repeats at file end by design — both copies are normative.)
Triggers
- User runs
/ds-benchmark - User asks to compare with competitors, learn from similar projects, or "what would ideal look like"
- User asks "am I doing this the right way" or "how do leading projects solve this"
- User preparing an OSS release and wants a credible positioning story
Triggers — INVOKE / DON'T INVOKE
| INVOKE | DON'T INVOKE |
|---|---|
| "compare with competitors", "what would ideal look like" | "audit my own code quality" (→ ds-review) |
| "ideal-vs-current gap table" | "score project health from inside" (→ ds-blueprint) |
| "OSS positioning research vs alternatives" | "marketing positioning / copy" (→ external / manual) |
| "am I doing this the right way" | "fix the issues you find" (→ ds-review / ds-fix) |
Contract
Dimensions: A1 (market positioning)
- Standalone; uses blueprint profile +
ds/audit/findings.mdwhen fresh (git_hash == HEADAND current run-cycle) to skip re-detection. - State-exempt: single regenerable report/audit.
- Full accounting enforced: every finding and planned check ends in an explicit disposition (fixed / skipped + reason / only you can do); summary totals balance.
- Pre-existing / out-of-scope errors detected during work are NOT skipped — fixed inline or escalated with concrete blocker.
- Research delegated to
/ds-researchwhen present — never re-implements CRAAP+ scoring. Absent → degraded inline search (Phase 3 fallback), all sources capped at T2 and labeleduntiered. - Writes
ds/audit/findings.md(scope=ideal-gap); contributes gap section to ds-ship report when invoked under it. - Zero autonomous architectural change. Every gap closure is Category B → user decision.
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.
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.
- 2d ago Changed · -4 lines 5ed87379c56e
- 5d ago First seen · 220 lines · 49 tokens per session scan A 3a5fab230218
ds-benchmark is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 4,241 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…
ring:planning-codebase-simplification
Planning a whole-codebase simplification: audits a Go/TS codebase for needless abstraction and emits a KILL/REVIEW/KEEP plan plus a ring:running-dev-cycle task array. Plans only — no edits. Detects single-impl interfaces, pass-through shims, translation-free adapters, and dead-code cascade chains under an inverted…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…