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/kirillsachkov/sachkov-stack/project-task-reportnpx skills add KirillSachkov/sachkov-stack --skill project-task-reportgit clone --depth 1 https://github.com/KirillSachkov/sachkov-stackWhat 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 | $0.00036 | $0.01068 |
| Opus 5 | $0.00018 | $0.00534 |
| Sonnet 5 | $0.00007 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
project-task-report 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Task Report
Publish one owner-facing completion report inside the task's canonical surface. The report is a completion artifact, not a session transcript, activity log, or global catalogue entry.
Decide whether the report is required
Require it when work belongs to a named project and the task is being completed after any of these:
- code, tests, configuration, data, documentation, infrastructure, or tracker state changed;
- an audit, diagnosis, investigation, or design decision produced a usable result, even with no file changes.
Do not require it for ordinary questions, casual discussion, unscoped research, or work still in progress. A blocked project task needs an explicit task-local handoff, but must not be marked done.
Choose exactly one canonical destination
Use the first available destination:
- Code work with a PR or MR: put the complete block at the top of its description.
- Tracker task without a PR or MR: put the complete block in that issue or work item.
- Project without a tracker: put the complete block in its brain task before moving it to
tasks/done/.
If a brain intake task is promoted into an external tracker, set a concrete frontmatter marker such
as promoted_to: gitlab#898, close the brain copy, and publish the eventual completion report only
in the tracker or PR/MR. The marker must be <provider>#<positive-id> or a full issue/MR/PR URL
ending in its numeric id; a provider homepage or arbitrary URL is invalid. A promoted brain task
must not contain a second report block.
Never create a separate report file, shared report directory, database row, or second full copy. The final chat response may link to the canonical report and summarize the outcome in one or two sentences; it does not replace or duplicate the report.
Author and validate
- Start from references/report-template.md. Keep the versioned markers and all seven headings unchanged.
- Write for an owner deciding whether the result is acceptable. Describe application areas and behavior, not merely file paths or commands.
- Set
Revisionto the delivery revision:- PR/MR code work: the final source-branch HEAD;
- tracker-free brain task: the repository HEAD immediately before the separate task-closure
commit (obtain it with
git rev-parse HEAD); - result without a code revision: a concrete task version or dated result identifier. Never leave a placeholder. The pre-closure HEAD rule avoids a circular commit hash while still binding the report to the implementation it describes. The closure commit must stage only task records; commit implementation and documentation first.
- State
Нет.when a required section has no risks, unverified work, or business-logic change. Do not leave a section empty or comment-only. - Validate the exact canonical content with the project's validator. The merge/closure gate must execute a trusted copy outside the source branch being checked; a vendored copy is useful for local feedback but is not the trust boundary. For a Markdown file:
What ships with it
3 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 First seen · 89 lines · 36 tokens per session scan A c76b988f0c84
project-task-report is a skill published in the GitHub repository KirillSachkov/sachkov-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,068 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…