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-docsnpx skills add sungurerdim/dev-skills --skill ds-docsgit 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-docs)<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-docs"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-docs.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 | $0.00064 | $0.05262 |
| Opus 5 | $0.00032 | $0.02631 |
| Sonnet 5 | $0.00013 | $0.01052 |
| Haiku 4.5 | $0.00006 | $0.00526 |
Grade A, and why
ds-docs 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 today.
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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ds-docs
Documentation drifts from code the moment it's written, decisions evaporate with no paper trail, and AI-harness context files silently bloat past the point they help. This skill detects the gaps, verifies claims against source code, tracks architecture decisions, and keeps harness context files signal-dense.
Documentation & Decision Integrity — doc-drift verification, gap generation, ADR tracking, harness-context-file curation.
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-docs, asks to check, generate, or improve documentation, asks "what docs are missing" / "is the README up to date", or asks to verify documentation accuracy against source code
Triggers — INVOKE / DON'T INVOKE
| INVOKE | DON'T INVOKE |
|---|---|
| "audit documentation gaps", "is README up to date" | "audit code quality" (→ ds-review) |
| "generate API docs from source" | "write marketing copy / landing page" (→ external / manual) |
| "verify docs against code (no drift)" | "test the documented examples" (→ ds-test) |
| "write ADR for this decision" | "research industry best practices" (→ ds-research) |
| "audit/trim my CLAUDE.md or AGENTS.md", "optimize my agent instructions file" | "configure harness permissions or install tools" (→ ds-rig) |
Contract
Dimensions: B5 (getting-started), B6, C3 (templates), C5 (deprecation), A10 (API doc completeness), D10 (support docs)
- Every generated sentence must earn its place — no filler, marketing language, or obvious statements.
- Only generates/modifies documentation files — never touches source code.
- Verifies claims against actual source code before writing.
- Standalone. Uses blueprint profile when available;
ds/audit/findings.mdonly when fresh (git_hash == HEADAND current run-cycle); own analysis otherwise. - 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.
- State-exempt: generated docs on disk are the progress record; re-running naturally resumes.
What ships with it
10 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.
- README.md 2.3 KB
- references/gap-analysis.md 7.3 KB
- references/rules-writing.md 25 KB
- references/scope-adr.md 2.5 KB
- references/scope-harness.md 3.3 KB
- references/template-breach-notification.md 6.5 KB
- references/template-dpia.md 5.7 KB
- references/template-privacy-policy.md 5.0 KB
- references/template-processor-registry.md 5.4 KB
- references/template-store-privacy-labels.md 5.3 KB
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.
- today Changed · -94 lines · +25 tokens per session aeb56325c896
- 3d ago First seen · 322 lines · 39 tokens per session scan A a61438d2b2bd
ds-docs is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 5,262 once invoked, about $0.0003 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: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: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:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…
api-integration-test
Create, maintain, and run gated Go integration tests for internal APIs and service-to-service clients (HTTP/gRPC). Use for endpoint verification, contract checks with real runtime config, opt-in execution, timeout/retry safety, and integration failure triage in Go services.
go-dependency-audit
Go dependency audit specialist for CVE scanning (govulncheck), license risk triage, outdated dependency detection, upgrade impact analysis, and supply chain security. ALWAYS use when auditing go.mod dependencies, running govulncheck, checking license compatibility, planning dependency upgrades, or investigating supply…
fuzzing-test
Generate Go fuzz tests (Go 1.18+ testing.F) for specified code when users ask for fuzzing/模糊测试/fuzz test generation, parser robustness, round-trip, or differential fuzzing. Always run an applicability gate first; if the target is not suitable, explain concrete reasons and stop without writing fuzz test code.