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 KirillSachkov/sachkov-stack --skill coding-task-pipelinegit clone --depth 1 https://github.com/KirillSachkov/sachkov-stackWrote 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/kirillsachkov/sachkov-stack/coding-task-pipeline)<a href="https://agentmods.dev/skills/kirillsachkov/sachkov-stack/coding-task-pipeline"><img src="https://agentmods.dev/badge/skills/kirillsachkov/sachkov-stack/coding-task-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/kirillsachkov/sachkov-stack/coding-task-pipeline"><img src="https://agentmods.dev/badge/skills/kirillsachkov/sachkov-stack/coding-task-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 | $0.00043 | $0.03538 |
| Opus 5.5 | $0.00017 | $0.01415 |
| Sonnet 5.5 | $0.00009 | $0.00708 |
| Haiku 4.5 | $0.00004 | $0.00354 |
Grade A, and why
coding-task-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 1mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Task Pipeline
Use this skill as the global quality contract for code-changing tasks. Keep the loop simple: define observable success, inspect the real system, isolate the task, implement from evidence, obtain independent review, verify the result, and leave a clean handoff.
Hierarchy
- Read the most specific applicable project workflow first. Treat this skill as the invariant base contract.
- Let project adapters override the issue tracker, base branch, branch naming, commands, CI, release route, and Definition of Done.
- Do not let an adapter silently weaken isolation, behavioral testing, independent review, fresh verification, or evidence. A user may explicitly approve a documented deviation, but waived core gates must be reported as incomplete and not pipeline-compliant.
- Keep stack details in repository instructions or focused skills. Do not copy framework-specific rules into this skill.
Skip this pipeline only for discussion, explanation, research without file changes, or a tiny read-only command result. Use the repository incident or release workflow when it applies, while preserving the evidence gates above.
Progress Contract
For a non-trivial task, track these gates in a plan or todo list. For a fast task, keep the same order in a compact form. Never skip a gate silently.
- Task contract
- Rules, stack, and reality check
- Research decision
- Task isolation and baseline
- Verifiable plan
- TDD implementation or deterministic non-code validation
- Self-review
- Independent review and blocker closure
- Fresh verification and acceptance
- Commits, integration, cleanup, and report
1. Task Contract
- Identify the source of truth: user request, issue, ticket, PR or MR, failing test, log, or repository task.
- Restate the goal as observable behavior. Separate constraints and non-goals from implementation ideas.
- Write acceptance criteria. Give every criterion an executable
verify:command or action. - Classify risk:
fast: documentation, typo, or mechanical configuration;standard: normal feature, bug fix, or refactor;high: authentication, authorization, money, migration, concurrency, infrastructure, destructive behavior, or sensitive data.
- Surface ambiguity that changes what to build. State a safe conservative assumption when possible; otherwise ask one focused question.
What ships with it
4 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.
- 1mo ago First seen · 242 lines · 43 tokens per session scan A d4a1bf7b0583
coding-task-pipeline is a skill published in the GitHub repository KirillSachkov/sachkov-stack (4 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 3,538 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…