continue-dev-flow

A tool for resuming approved repository work through a selected proof-of-concept, pilot, or production route. It restores the relevant workflow rules, work item, brief, branch, and delivery state.

In plain words
What is it for?
Use it when continuing an adopted repository's work, especially when selecting a delivery stage, restoring its requirements, or building on an open unmerged change.
Why use it?
It helps continue work without rereading unrelated project history or losing track of the correct branch and approval route. It also checks existing reviewable work before creating or reusing a branch.

Skill for Claude CodeCodex

Part of the kc-dev-flow plugin — 6 skills shipped together

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/iamcxa/kc-claude-plugins/continue-dev-flow
Any agent
npx skills add iamcxa/kc-claude-plugins --skill continue-dev-flow
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Made for: Claude Code, Codex.

Or install kc-dev-flow, the plugin that ships this one along with the rest of its 6 skills.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,327 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 $0.00034 $0.03327
Opus 5 $0.00017 $0.01664
Sonnet 5 $0.00007 $0.00665
Haiku 4.5 $0.00003 $0.00333

Measured 2d ago against content hash ca39b3c11899, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

continue-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 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.

kc-dev-flow/skills/continue-dev-flow/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continue Dev Flow

Continue by the selected profile's smallest sufficient route.

Resolve authority before policy

  1. Locate the workflow README via the nearest repository instructions. Require the unique ordered kc-dev-flow-static-local-profile start/end marker pair, with ## Local Profile immediately after start. Read only its frontmatter and marked block; never infer boundaries from headings or open the full README.
  2. Recheck the worktree, branch, shared-state owner, and remote delivery state. When this item is delivered through a reviewable delivery artifact, list the open artifacts before creating or reusing a branch. An open unmerged artifact that carries work this item builds on is the default base: branch from its source branch and stack, rather than branching from the trunk or waiting for it to merge. delivery-branch-base.md owns the rule and its exceptions, and applies whoever owns the delivery ceremony.
  3. Read the exact committed work item and selected brief. A Pilot or Production new admission requires one Development Brief containing the problem, accepted outcome, complete non-goal list, route-back conditions, and one canonical ## Acceptance criteria section with unique ascending AC-N bullets. A POC item uses its complete v3 decision, falsifier, budget, and stop condition as the Exploration Brief. Do not read current execution state or revalidate and rewrite an already-admitted item's historical headings.
  4. Classify its optional Planning Receipt before provider access. The receipt is exactly source, planning-window, and planning-outcome:
    • when all Planning Receipt fields are absent, use the Captain-approved committed brief as planning authority and do not invoke a provider reader or comparator;
    • when all Planning Receipt fields are present, run provider reconcile only for the provider-backed branch below. For a new Pilot or Production admission, first invoke the repository-local profile loader's explicit --validate-admission mode; default continuation never selects that mode; and
    • otherwise report planning receipt incomplete and stop before reading execution state or mutating it.
  5. In the provider-backed branch, follow the exact work item's source to the accepted planning item and invoke the repository-local read-only planning reader. Read the item for the problem, decision, success condition, priority, and human-facing status, and obtain the union of the provider's current Ready set for the recorded planning window/outcome and every currently Ready snapshot source even when its current window or outcome moved. Refuse a truncated provider result. If source is not a resolvable planning link, report planning source unavailable and stop before reading execution state. If the reader or its inputs are unavailable, report planning reconcile unavailable and stop at the same boundary. Do not promote the admission snapshot into planning authority or invent, migrate, or rewrite its planning item.
  6. Still in that branch, compare the current Ready set with the committed execution snapshot selected through the adapter's local grouping. Compare source identity and membership, planning-window, planning-outcome, accepted goal, and non-goals; classify each difference as added, removed, changed, or moved. Normalize both sets into ephemeral JSON lists whose items contain source, planning-window, planning-outcome, accepted-goal, and string-list non-goals. Do not commit or reuse those files. Refuse the snapshot unless every item shares the exact window and outcome read from the engaged item.
  7. Invoke the repository-local read-only engage comparator only in the provider-backed branch.

Read the full file on GitHub · 259 lines

Files

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.

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. 2d ago First seen · 259 lines · 34 tokens per session scan A ca39b3c11899

Subscribe to this mod's changes

continue-dev-flow is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 3,327 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 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