insert-defect

A workflow for adding a new bug to a live DevStride project plan, placing it in the dependency order and giving it a date.

In plain words
What is it for?
Use it to capture a defect, optionally under a parent project item, and insert it into the live roadmap.
Why use it?
It records newly found bugs where the next build cycle will pick them up, without pretending they were part of the original plan.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/devstride/claude-plugin/insert-defect
Any agent
npx skills add devstride/claude-plugin --skill insert-defect
Clone the repo
git clone --depth 1 https://github.com/devstride/claude-plugin

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.03230
Opus 5 $0.00015 $0.01615
Sonnet 5 $0.00006 $0.00646
Haiku 4.5 $0.00003 $0.00323

Measured yesterday against content hash 32891381bec9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

insert-defect 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.

skills/insert-defect/SKILL.md · 83 lines

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.

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.

Insert a NEW Defect (the one-day leaf role — this org's Defect type) into a live DevStride roadmap — spliced into the dependency chain and dated so the /devstride:build-item loop picks it up NEXT. Its POSITION in the sequence looks native to the plan; its DESCRIPTION stays an honest repro/root-cause of the real bug (see the IMPORTANT note below — this is a splice/date operation, not a fabricated history). This is also the canonical capture path that build-item step 6.5 and ultracode-build use to turn a newly-discovered defect into tracked, dependency-ordered work.

Argument — free text describing the defect, optionally prefixed/suffixed with a parent item number (any grouping level of your org's hierarchy, e.g. this org's Module/Capability/Epic — as in I20100 webhook retries duplicate on 429 or just webhook retries duplicate on 429): $ARGUMENTS

IMPORTANT — the DevStride MCP targets PRODUCTION (api.devstride.com). Every create/update here is a real, user-visible change to the live plan.

IMPORTANT — this is a Gantt-grooming skill: it changes DevStride data only, never the repo. If the user also wants code changes, that's a separate /devstride:build-item run AFTER this item exists.

0. Resolve the parent and read the plan

  • First, require enough to act on. If $ARGUMENTS carries no real description of the bug (just an item number, or an empty/vague invocation), STOP and ask the user for the repro and expected-vs-actual behavior before creating or splicing anything — do NOT invent one.
  • If $ARGUMENTS contains an item number (I#####), that is the anchor — get_item(view:"full") it, and resolve the org's REAL container/leaf work type names via get_work_type_hierarchy to classify it (never assume the literal Capability/Epic/Defect names). If it's a top-level container (this org's Module), you'll need to find/create a housing container at the level below (step 2). If it's already a lower-level container (this org's Capability or Epic), it IS the direct parent.
  • If no item number is given, ask the user which parent item (any grouping level — this org: Module/Capability/Epic) this defect belongs to — do NOT guess at a plan to insert into.
  • Pull the full descendant tree under the resolved anchor with search_items (hierarchy=[anchor], itemType=workitem, no isDone filter, limit 200) to see the current shape: which children are containers and which are executable leaves (this org: Capabilities/Epics vs Stories/Defects), their lanes, and their dates.
  • For each candidate container in that tree, fetch its blocked_by/blocks relationships (get_item(view:"full", fields:["number","relationships"])) — for a big tree, fan this out with a Workflow (chunks of ~10 items/agent) rather than serial reads.

Read the full file on GitHub · 83 lines

Changes

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.

  1. yesterday First seen · 83 lines · 29 tokens per session scan A 32891381bec9

Subscribe to this mod's changes

insert-defect 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 3,230 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens