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/devstride/claude-plugin/rationalize-ganttnpx skills add devstride/claude-plugin --skill rationalize-ganttgit clone --depth 1 https://github.com/devstride/claude-pluginWhat 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 | $0.00030 | $0.02428 |
| Opus 5 | $0.00015 | $0.01214 |
| Sonnet 5 | $0.00006 | $0.00486 |
| Haiku 4.5 | $0.00003 | $0.00243 |
Grade A, and why
rationalize-gantt 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human output. Read ${CLAUDE_PLUGIN_ROOT}/skills/build-item/references/plain-language-output.md once per top-level run; composed skills reuse it. Apply it to every message.
Backfill synthetic dates and rationalize the dependency graph of a DevStride plan so its Gantt renders as a maximally-compressed, gapless, fully-valid dependency cascade. Use it after building out (or partway through) a plan whose item dates have drifted, gone stale, sit in the future, or never reflected the real blocked_by graph — and to surface/clean up wrong or coarse dependencies (the red "invalid dependency" lines are a free lint of your plan graph). Assumes every story takes exactly ONE day — the Claude Code build pace — so the timeline is a synthetic critical-path view, not a forecast.
Plan-root argument — the item number whose descendant tree IS the plan (a parent item at any
grouping level of your org's hierarchy — e.g. this org's Solution or Epic — or a workstream; e.g.
I20100), or a roadmap/Gantt name; empty → ask which plan to rationalize: $ARGUMENTS
IMPORTANT:
- The DevStride MCP targets PRODUCTION. Every date and relationship change here is a real, user-visible edit to live items. The cascade OVERWRITES existing start/due dates across the whole tree — including the real completion-ritual dates set by
build-item. Confirm the scope root (and whether completed items are in scope) before mutating. - This is a Gantt-grooming skill — it changes DevStride data only, never the repo.
- Re-date ONLY — never renumber. Leaf-item titles carry stable bracketed execution-order prefixes (
[N],[23.1]) per the CANONICAL NUMBERING CONVENTION —${CLAUDE_PLUGIN_ROOT}/skills/plan/references/execution-order-numbering.md— which are INDEPENDENT of the synthetic dates this skill computes. Do NOT touch, re-sequence, or "fix" title prefixes here even when the recomputed cascade reorders items on the timeline — write onlystartDate/dueDate(step 4) and relationships (step 6), nevertitle. Prefixes disagreeing with date-order is expected per that convention — leave it. - Goal state: every story is 1 day, each dependency sits on the immediately-preceding day(s), there are NO empty days, and there are NO red (invalid) dependency lines. "Compress as much as possible AND display only valid dependency dates."
0. Scope + confirm
- Resolve the plan root from
$ARGUMENTS(or ask). Pull the full descendant tree withsearch_items(hierarchy=[root], itemType=workitem, noisDonefilter, limit 200) → the node list withnumber/title/parentNumber/lane/dates. - Confirm with the user, because each materially changes the output: (a) the root; (b) re-date completed items too, or only not-done? (default: everything, for one clean cascade); (c) confirm the 1-day-per-story assumption.
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.
- 2d ago First seen · 69 lines · 30 tokens per session scan A 8da2c3c961e3
rationalize-gantt is a skill published in the GitHub repository devstride/claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 2,428 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.
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.