Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add iamcxa/kc-claude-plugins/plugin install kc-dev-flow-2Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/dev)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/dev"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/dev"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01080 |
| Opus 5.5 | $0.00014 | $0.00432 |
| Sonnet 5.5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
dev 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev
Invocation: kc-dev-flow-2:dev
Package root: ${CLAUDE_PLUGIN_ROOT}
<package> in this skill and its linked files is this root. If the value above
is not an absolute path, the root is two directories above this SKILL.md.
Read the framework. This is a start/resume entry, not a worker
stage or a second workflow controller. Claude's packaged command is
/kc-dev-flow-2:dev; bare /dev is not a promised cross-host alias.
Resolve the absolute project root, explicit workflow directory and intended work item from the request and authoritative project/task records. Reuse established context; do not guess between projects or tasks. Read applicable project conventions and the existing context needed for the requested work.
After resolving the code root, run python3 <package>/scripts/learning.py --repo <absolute-code-root> notices --all. Present relevant unread learning results (items
with unread true) to the user, distinguishing pending/uncertain, no-change, local proposal, PR and observed
merge; pending proposals are not active rules. Only after actual presentation,
run ack --job <job> --expected <notice_digest> for each shown snapshot. Context
injection or reading alone is not presentation. A changed digest stays unread;
interruption may repeat a notice. Settle every delivery shown open, acknowledged or not, by reading its PR
with gh pr view as learn's Follow the delivery to a recorded end says, before presenting.
Read failure holds that learning action, not
unrelated approved development. This entry-level check is not a host SessionStart
hook. Use learn for an explicitly requested named-task loop;
notices do not authorize evaluation, delivery, retry or merge.
For existing work, preserve its recorded variant/profile, approved outcome, scope, non-goals and stop condition. Read current state, reports and delivery status instead of assuming a prior conversation is current. An invalid profile, conflicting records or missing authority holds the dependent action; return only the unresolved decision to the user. Do not restart approved design or ask again for an unchanged selection.
For new work without a profile selection, establish the intended outcome and recommend a profile using the framework's intended use and applicable shared profile principles. Ask the user to select it before profile-dependent work. An explicit valid selection is sufficient; FO records it with the variant in the work item through the existing workflow. Recommendation is not selection.
Hand the resolved project root, explicit workflow directory, work item, approved
selection/scope and bounded outcome to spacedock:first-officer, with this
skill's Package root: value, which FO writes into the scope notes of every
worker dispatch and follow-up message with a line telling the worker to send its completion
message to main, because the completion block Spacedock appends names team-lead. Retain that
workflow directory as --workflow-dir on SD commands; cwd alone is not the
binding. If FO is already active, continue there. SD owns stage selection, live
worker availability, dispatch, reports, gates and recovery; a resumed FO does
not establish that its old worker still exists. An entity sitting in a stage
declared gate: true is excluded from spacedock status --next and from
--boot's DISPATCHABLE table before the concurrency check runs (Spacedock
v0.27.0, internal/status/format.go, dispatchAnalysis, reason gate), so an
empty dispatchable view does not mean no worker is available; three of this
workflow's five stages (backlog, ideation, validation) declare gate: true,
so that empty view is this workflow's normal case, not the exception. Stage
skills own profile routing and load the selected references in each worker's
context.
Before each worker dispatch and on resume, run python3 <package>/scripts/workflow_checkout.py <workflow-dir>/README.md. Exit 1 means the README FO follows differs from the trunk's,
exit 2 that it could not be compared; hold the dispatch, show the Captain the printed
remedy or cause, and wait. Do not run the remedy or move the checkout yourself. This
sentence sits here because a README old enough to be wrong may not contain 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.
- 2d ago Changed · -5 lines 7a40c33563f1
- 4d ago Changed · +14 lines 94943463355e
- 18d ago Changed · +6 lines 42c2db790109
- 1mo ago Changed · +18 lines b1e8e14cebeb
- 1mo ago First seen · 46 lines · 34 tokens per session scan A 0672f1ce28e4
dev is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,080 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.