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/sdcorejs/sdcorejs-agent/sdcorejs-execute-plannpx skills add sdcorejs/sdcorejs-agent --skill sdcorejs-execute-plangit clone --depth 1 https://github.com/sdcorejs/sdcorejs-agentWhat 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 | $0.00104 | $0.05589 |
| Opus 5 | $0.00052 | $0.02795 |
| Sonnet 5 | $0.00021 | $0.01118 |
| Haiku 4.5 | $0.00010 | $0.00559 |
Grade A, and why
sdcorejs-execute-plan 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
04 - Execute Plan
Shared Protocols
Read _refs/shared/runtime-protocols.md. Apply
_refs/shared/artifact-lifecycle.md and preserve/merge artifact_context from
the approved spec, plan, and every producer. Use these executable sources of
truth before any write or dispatch:
_refs/shared/approved-artifact.mjsfor approval identity and parent graph._refs/shared/system-registry.jsonfor track/profile routing._refs/shared/decision-coverage.mdand its executable validator for strict decision/task/path/evidence coverage._refs/shared/architecture-contract.mjsfor the conditional approved architecture graph, exact handoff identity, and invariant ownership._refs/shared/convergence-contract.mjsfor exact executed task/change trace rows._refs/orchestration/execution-contract.mjsfor execution preparation, current-root/path authorization, owner routing, working-tree boundaries, and execution-mode selection.
Purpose
Run the approved plan as the execution contract. This skill is the handoff between planning and doing.
It owns four decisions:
- Which execution track should run.
- Whether sequential execution is required or a real sequential/parallel choice exists.
- Whether Angular work is Core UI portal work or plain Angular work.
- Whether NestJS, Next.js, React, Node/general, migration, product, design, or test work needs a track executor or the generic harness fallback.
The generic harness is write-capable because it is the approved-plan fallback
executor for unsupported stacks and explicit CREATE/EDIT tasks. Write
permission is constrained by plan_context.allowed_paths,
plan_context.prohibited_paths, dependency/env/migration boundaries, and the
working-tree preflight below.
Preconditions
- The approved spec and plan snapshots are available as paths or in context.
plan_contextis present, includingapproved_spec_hash,approved_plan_hash,target_root_kind,stack_profile,allowed_paths,prohibited_paths, dependency/env/migration boundaries, verification strategy, and parallel candidates.
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 · 503 lines · 104 tokens per session scan A 597a05813710
sdcorejs-execute-plan is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 104 tokens to every session and 5,589 once invoked, about $0.0005 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.