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/iamcxa/kc-claude-plugins/adopt-dev-flownpx skills add iamcxa/kc-claude-plugins --skill adopt-dev-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/adopt-dev-flow)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/adopt-dev-flow"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/adopt-dev-flow.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.03649 |
| Opus 5 | $0.00019 | $0.01825 |
| Sonnet 5 | $0.00008 | $0.00730 |
| Haiku 4.5 | $0.00004 | $0.00365 |
Grade A, and why
adopt-dev-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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adopt Dev Flow
Bind the existing repository to one shared core and profile-native routes. Do not replace a working planning provider, workflow runtime, or delivery provider.
Audit
Read ../../references/kernel.md and the existing repository authorities. Map
project context, required briefs, any planning provider, local execution
groups, execution state, delivery, scope, and observation. A provider-backed
item keeps one external planning authority and a complete Planning Receipt; a
standalone item uses its Captain-approved committed brief. The workflow runtime
owns only its admitted snapshot, execution record, and evidence. Each item has
one planning authority and one execution-record authority. Classify the relevant
seams as working, broken, stubbed, or missing; repair the cheapest compatible
seam. Before interpreting an existing source as Planning Receipt data,
preserve repository-local free text in a repository-owned field and remove the
canonical source field. Do not reinterpret provenance as provider identity.
Adopt
- Add a concise
## Local Profilenear the workflow frontmatter, bounded by exactly one start marker<!-- kc-dev-flow-static-local-profile:start -->and one end marker<!-- kc-dev-flow-static-local-profile:end -->. Bind existing authorities plusInstalled contract interface,Local mods, and the repository's work-item and state authorities. The activated skill anchors its own package root and supplies../../scripts/profile-contract-loader.pyfor that invocation; do not persist an installation path. A repository that supports Planning Receipts binds its provider, read-only reader, and installed engage comparator. Linear uses installed siblinglinear-admission.py; other providers keep a repository-local adapter. That sibling needsLINEAR_API_KEYin the invoking process environment, which is provider credential rather than host binding, and a state authority at<workflow-dir>/.spacedock-statethat is its own committed git root. It reads no other environment variable to decide whether to run, so a VM, a CI runner, and a plain shell are all supported hosts. A repository whose state lives inline in the workflow directory has no such root; the reader refuses it withstate authority is not <workflow-dir>/.spacedock-state, so raise that layout as a refit requirement against the package and keep the repository-local adapter until then. Work with no planning provider at all records no Planning Receipt, invokes no reader, and needs no credential. The reader normalizes the union of current Ready items for one planning window/outcome and every currently Ready snapshot source even when it moved; it refuses a truncated result and exposes source identity, accepted goal, and non-goals without writing either system. A standalone adopter binds the Captain-approved committed brief and installs no provider adapter. Do not mirror live provider status into a Roadmap or execution record. - Read
../../contract-manifest.jsonbeside the activated skill. It declares the contract interface, Local Profile interface, and exact plugin-owned runtime resources. Run its sibling installed loader from that same package; do not search host caches, inspect host names, copy canonical resources into the repository, or add a repository fallback. Provider-backed work uses its reader and installedengage-reconcile.py; standalone uses neither. The selected stage owns each typed conditional-reference trigger; installation does not load a reference. Local provider paths, README policy, local mods, and Spacedock state remain repository-owned. The manifest'sresourceslist is the boundary for what adoption adds to the repository: adoption binds existing repository authorities and adds no repository-owned reader, adapter, script, test, or check for a capability a declared resource already supplies. A capability the package lacks is a refit requirement raised against the package, with one exception: a planning provider the package does not support keeps a repository-local adapter. - Select a profile before the first working stage and store the v3 receipt in
the existing work item. Each item selects independently; do not create a
project-global profile or another profile registry. Invoke the loader with
the exact work item so simultaneous items cannot borrow each other's route.
Require the Development Brief for Pilot and Production or the v3 Exploration
Brief for POC. A Planning Receipt is complete or absent: provider-backed work
records
source,planning-window, andplanning-outcome; standalone work records none of them. A partial tuple stops. Localsprintandsprint-readinessremain runtime grouping and readiness mechanics, not planning evidence. When the provider uses Issue bodies as admission packets, each body starts directly with## The problemand omits both an## Agent execution contractsection and a## Human-readable release briefwrapper, carrying these headings in this order:
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.
- today Changed · +34 lines fcb95baf1dcc
- yesterday Changed · +26 lines ba542831740e
- 5d ago First seen · 209 lines · 39 tokens per session scan A bcc4b365b127
adopt-dev-flow is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 3,649 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.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…