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 skills add iamcxa/kc-claude-plugins --skill maintain-flowgit clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsWrote 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/maintain-flow)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/maintain-flow"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/maintain-flow/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/maintain-flow"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/maintain-flow.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 | $0.00046 | $0.01215 |
| Opus 5.5 | $0.00018 | $0.00486 |
| Sonnet 5.5 | $0.00009 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
maintain-flow 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 today.
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.
Maintain flow
Invocation: kc-dev-flow-2:maintain-flow
Read the framework and the affected skill's routing table. Put cross-stage profile principles in their one shared reference, stage-common practices in principles.md, and differences in that stage's profiles directory. Preserve exact variant namespaces and the POC ideation skip; avoid copying a shared rule into each profile or adding unused automation scaffolding.
Every adopter copies references/sd/workflow.md as its workflow README, and the
implementation and validation stages inline its context-sections into each
dispatch, so its text costs every FO and worker. For each rule added to it,
state in the change: the incident it answers; whether a package script, test or
SD command already enforces it, in which case write one sentence naming that
enforcer instead of restating it; and which existing sentence it replaces, or
that it replaces none. Before adding, look for a sentence to shorten or remove.
Report the file's word count before and after, and the words each worker stage
inlines. kc-dev-flow-2/scripts/lint-skills.py refuses a file whose count differs from its word budget and a passage of
12 or more words that another package file repeats; a raise of the budget needs a Captain ruling
in the budget steps, a cut lowers it in the same change, and listing an overlap says why.
Run python3 kc-dev-flow-2/scripts/lint-skills.py from the repository root. Before each push
of a package change, run python3 kc-dev-flow-2/extensions/roborev/roborev_gate.py --repo <worktree> --base <merge base> and fix what it reports inside the change: a maintainer
change is not dispatched through FO, so no implementation stage runs it.
When changing lint behavior, run python3 kc-dev-flow-2/scripts/test_lint_skills.py
and add a mutation only for a material failure the check is meant to catch.
Use an available Agent Skills specification validator for broader authoring
format checks; the bundled CLI reuses the repository's basic frontmatter check
and validates declared routing structure and package script paths, not the full
standard or agent behavior.
An optional tool joins as an extension: a folder kc-dev-flow-2/extensions/<name>/ holding
its scripts, their tests and an EXTENSION.md in the shape of the existing ones. The workflow
mentions extensions only in its ## Extensions section and the README's extensions: list,
so a repository that lists none is unchanged.
A script that newly needs a line or step only FO writes must also print it from a script the previous release's README already has FO run at that moment, shown by running the new scripts over the previous release's record shape; no check enforces this.
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.
- today Changed · +4 lines 963030f46a57
- 4d ago Changed · +1 lines a14b9174ff22
- 5d ago Changed · +19 lines c4d4bbd87e5b
- 6d ago Changed · +20 lines 7f443e70a147
- 8d ago Changed · +12 lines · +18 tokens per session a153945e574e
- 18d ago Changed · +1 lines 5f1913c5e4ea
- 1mo ago First seen · 26 lines · 28 tokens per session scan A b209d0d62632
maintain-flow is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,215 once invoked, about $0.0002 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.