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/comprehend-plannpx skills add devstride/claude-plugin --skill comprehend-plangit 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 | $0.00029 | $0.01465 |
| Opus 5 | $0.00015 | $0.00732 |
| Sonnet 5 | $0.00006 | $0.00293 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
comprehend-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 yesterday.
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 — 66 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.
Recursively read a DevStride plan — descriptions AND comments, at every level — to build a full, grounded understanding of what a parent item at any grouping level of your org's hierarchy (e.g. this org's Module/Capability/Epic) actually contains, where it stands, and what its real (not just titled) intent is. This is a READ-ONLY research skill: it never creates or edits DevStride items, and never touches the repo.
Plan-root argument — the parent item number to comprehend (any grouping level of your org's
hierarchy, e.g. this org's Module/Capability/Epic — such as I20100), optionally followed by a
focus question (e.g. I20100 what's left before webhook intake is done?); empty → ask which item to
comprehend: $ARGUMENTS
Use this BEFORE /devstride:insert-story, /devstride:insert-defect, /devstride:rationalize-gantt, or any surgical edit to a plan you don't already carry full context on — and any time the user asks "what's the state of X" / "what does X actually cover" / "where are we on X".
0. Resolve the root
- Parse
$ARGUMENTSfor a leadingI#####/F#####item number; the remainder (if any) is a focus question to keep in mind while synthesizing (step 3) — it does not narrow what gets read. - If no item number is present, ask which plan to comprehend. Do not guess.
get_item(view:"full")the root to confirm its work type (a container level — this org: Module/Capability/Epic; resolve unfamiliar names againstget_work_type_hierarchy) and pull its own description.
1. Pull the full descendant tree
search_items(hierarchy=[root], itemType=workitem, noisDonefilter, limit 200) to get every descendant: number, title, workType, parentNumber, lane, dates. This is the shape of the plan — containers (this org: Modules/Capabilities/Epics) and executable leaves (this org: Stories/Defects).- If the tree exceeds ~200 items, page
search_itemsor scope by an explicit sub-branch and tell the user you scoped it.
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.
- yesterday First seen · 66 lines · 29 tokens per session scan A 69cf64cb72f7
comprehend-plan is a skill published in the GitHub repository devstride/claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 1,465 once invoked, about $0.0001 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…