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/ahepi/deepreason/dr-plan-stepsnpx skills add AHepi/DeepReason --skill dr-plan-stepsgit clone --depth 1 https://github.com/AHepi/DeepReasonWhat 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 | $0.00049 | $0.01001 |
| Opus 5 | $0.00024 | $0.00500 |
| Sonnet 5 | $0.00010 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
dr-plan-steps 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan the steps
Input: SPEC.md (re-read REQUEST.md and SPEC.md in full first). Output: CHECKLIST.md — the complete ordered path from the current tree to the accepted change. Execution will do NOTHING that is not a step here, so missing steps here means missed work later. Plan against that.
Ordering rules
- Dependencies first, verification interleaved: a step that writes a test precedes the step whose change it guards; a step that runs a check follows immediately after the change it checks — not batched at the end where failures lose their cause.
- One step = one action with ONE done-criterion (a command and its expected output, or "file exists containing "). If a step needs the word "and", split it.
- Include the boring steps that get forgotten — they are the point of
this skill: creating directories,
chmod +x, updating the ladder or docs SPEC says to update, retiring an occupied run root (rename commit FIRST), the subsystem test ring, the FULL gate (pytest tests/ -q -n 4, expect 0 failed), the tranche commit with its message, the push with retry, and the finalgit status --porcelaincleanliness check. - Every step cites its spec item (S-number). A step with no S-number is scope creep — delete it or send it to PARKED.md.
- Scope from the map before planning steps. Open
docs/map/INDEX.md, resolve the change toDR-SUB-/DR-CON-/DR-SEAM-ids, and read the seam document before the subsystem ones — the file isdocs/map/SEAM-<a>-x-<b>.md, sides in alphabetical order, and the worked recipe for a seam change isdocs/map/REC-change-a-seam.md. Name those ids in CHECKLIST.md's header so execution starts from the same map the plan was built on. A change whose ids you cannot name is a change you have not scoped. - Plan the map update as part of the step that changes behaviour, never as a trailing "update docs" step. A trailing documentation step is the one that gets dropped when a tranche runs long. If a seam document must be CREATED, that is its own step, and it comes BEFORE the code steps — writing down the agreement is how you find out whether you understand it.
- Mark checkpoint steps
[COMMIT]at natural boundaries (at minimum: after tests-written, after each spec item lands, after the gate) — rationale canonical indr-drive-harness§1.
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 · 83 lines · 49 tokens per session scan A 6460c2aefb34
dr-plan-steps is a skill published in the GitHub repository AHepi/DeepReason (140 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,001 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 2026-08-30.
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.