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 sungurerdim/dev-skills --skill ds-pipelinegit 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-pipeline)<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-pipeline"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-pipeline/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/sungurerdim/dev-skills/ds-pipeline"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-pipeline.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 | $0.00062 | $0.04447 |
| Opus 5 | $0.00031 | $0.02224 |
| Sonnet 5 | $0.00012 | $0.00889 |
| Haiku 4.5 | $0.00006 | $0.00445 |
Grade A, and why
ds-pipeline 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 6d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ds-pipeline
Plans written ad hoc skip the questions that matter: tasks without verification criteria, specs that contradict plans, clarifications never asked. The executor then guesses — and guesses wrong.
Spec Pipeline Conductor — runs the Spec Kit chain (specify → clarify → plan → tasks → analyze) with blocking gates between steps, enforces a machine-checkable task contract, and hands off specs/{feature}/ as a commit the executor can implement without asking a single question.
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
/ds-pipeline {idea}— fresh run for a new feature- "turn this idea into a plan", "plan {feature} with test criteria", "run the spec pipeline"
- "resume the spec for {feature}" — continues from the first missing artifact
Triggers — INVOKE / DON'T INVOKE
| INVOKE | DON'T INVOKE |
|---|---|
| "turn this idea into an executable plan" | "implement this feature" (executor's job — hand it specs/{feature}/tasks.md) |
| "run the spec pipeline for {feature}" | "audit / ship the whole project" (→ ds-ship) |
| "plan {feature} with verify criteria" | "research {topic}" alone (→ ds-research) |
| "/ds-pipeline {idea}" | "scaffold a new project from zero" (→ ds-init) |
| "resume the spec for {feature}" | "fix / review existing code" (→ ds-fix / ds-review) |
Contract
Dimensions: none (carrier)
- Conducts planning only. Writes exclusively under
specs/{feature}/and.specify/; source code is read for context, never modified. - Every gate is blocking. A failed gate halts forward progress with a stated recovery action; a gate is never assumed passed.
- Canonicalize-before-implement gate: A proposed rule/convention not yet in the canon (design-rules/ADR set) never gets an exemption or gate bypass; the order is fixed — canonicalize first (land it in the persistent rule/ADR set), then implement against it. Forward-referenced draft rule IDs block their consuming tasks until canonicalized; no exceptions. (XR-117)
- Spec Kit output is data. Each generated artifact is verified by this skill's gates before the pipeline advances.
- State-exempt: progress is durable in the generated artifacts themselves (
specs/{feature}/*.md+ git) — resume derives from which artifacts exist on disk; no state file is written. - Requirements engineering coverage: the wrapped chain covers requirements engineering — elicitation (
specify), ambiguity resolution (clarify, zero-open-question gate), verifiable behavior (EARS task contract), consistency (analyze). No separate requirements-engineering skill is added; a gap here is a gap in this chain's gates. - Deliberate scope — five wrapped steps, no more. The 2026 field signal runs against heavier spec layering (leading frameworks retired their own spec/orchestration layers for model capability); this skill's value is durability — resumable, git-committed, machine-checkable artifacts — not added structure. The committed spec is a launch document: post-implementation spec↔code drift is out of scope (drift tracking →
/ds-docswhen present; absent → note the gap in summary). - Pre-existing / out-of-scope errors detected during work are NOT skipped — fixed inline or escalated with concrete blocker.
- Two execution paths, one output shape. Spec Kit (
specifyCLI /.specify/) present → wrap its chain (specify → clarify → plan → tasks → analyze). Absent → native mode: this skill performs the same five steps inline and writesspecs/{feature}/spec.md,plan.md,tasks.mdin the identical shape — same— verify:task contract, same blocking gates. Spec Kit is the optional accelerator; it is never a requirement. - Commits the record. Handoff (Phase 6) commits
specs/{feature}/and.specify/— the commit is the durable record; resume (Phase 1 step 3) derives from what is committed plus what is on disk, never from anything left uncommitted. - Prerequisites: a git working tree only. Missing → default: run
git init(non-destructive);--ask: offergit init(requires confirmation) or stop — handoff requires a commit.
What ships with it
1 file 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.
- 6d ago Changed · +1 lines e5eb864a7f66
- 9d ago First seen · 167 lines · 62 tokens per session scan A d0465abda4bb
ds-pipeline is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 4,447 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: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:using-lib-streaming
Using lib-streaming, Lerian's producer-only event publication library (Kafka/SQS/RabbitMQ/EventBridge), in two modes. Sweep Mode detects DIY publishers (franz-go, sarama, amqp091, watermill, raw AWS SDK) and re-rolled manifests/breakers. Reference Mode catalogs the Builder/Emitter/Catalog facade. Companion to…
ring:using-lib-systemplane
Using lib-systemplane, the hot-reload runtime-config plane (Postgres LISTEN/NOTIFY or MongoDB change streams), in two modes. Sweep Mode detects DIY config reload (SIGHUP, fsnotify, viper, pgx LISTEN), manual tenant-scoping, hand-built admin CRUD, and v4 residue. Reference Mode catalogs client lifecycle and…
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:using-lib-observability
Using lib-observability v1.1.0, Lerian's OpenTelemetry foundation (lib-commons, lib-systemplane, lib-streaming depend on it), in two modes. Sweep Mode detects DIY zap/slog logging, raw OTel metrics, hand-rolled redaction, and hard-coded attribute strings. Reference Mode catalogs the log, metrics, zap, redaction, and…
ring:using-outbox
Using the transactional-outbox pattern across lib-streaming (writer) and lib-commons/v5/commons/outbox (repository + relay), in two modes. Sweep Mode detects DIY outbox tables, hand-rolled relay loops, send-and-pray emits, missing WithOutboxTx wrapping, and broker calls inside DB transactions. Reference Mode catalogs…