work

work is a skill for Claude Code from fledgeling-co/fledgeling-plugins. It costs 198 tokens per session (4,435 once invoked), scanned A, original, MIT.

A build workflow for implementing a planned feature in an isolated Git worktree, which is a separate working directory for a branch. It also records evidence that the work was completed and checked.

In plain words
What is it for?
Use it to read the plan and design, build the feature, run its required checks, and leave the branch with a completion record.
Why use it?
It keeps feature work separated from other changes and provides a structured path from an approved plan to implementation and self-verification.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the shipyard plugin — 8 skills shipped together

Good fit Use it to read the plan and design, build the feature, run its required checks, and leave the branch with a completion record.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add fledgeling-co/fledgeling-plugins
Claude Code
/plugin install shipyard

Made for: Claude Code.

Or install shipyard, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for work

README.md
[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/work/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/work)
Your own site
<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/work"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/work/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.

agentmods 80×15 button for work

Your own site · 80×15
<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/work"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00198 $0.04435
Opus 5.5 $0.00079 $0.01774
Sonnet 5.5 $0.00040 $0.00887
Haiku 4.5 $0.00020 $0.00443

Measured 1mo ago against content hash faae488615cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

work 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 1mo 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.

plugins/shipyard/skills/work/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline Worker — build, evidence, and self-verification

Implement a planned feature inside an isolated worktree, driven by dynamic workflows, and leave the branch local with an evidence-typed completion record. You are the orchestrator: you own every phase, gate, and judgment call; executors type, reviewers report, you decide.

Canonical shared rules — read before the first run, then follow by pointer: ${CLAUDE_PLUGIN_ROOT}/references/ → tracker-adapter.md (substrate, statuses, comments), model-lanes.md + model-and-effort.md (routing, REVIEWER ≥ WRITER, effort discipline), executor-lanes.md + codex-cli.md (delegation), evidence-rules.md (what closes a claim), test-strategy.md (the coverage bar), operational-rules.md (git/worktree/fan-out incidents).

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It gives every categorical scope in the build a denominator, turns each phase gate into pasted command output with its prerequisite artifact checked first, and reads the skill's caps back off git rather than off its own prose. Other models skip it.

Inputs

  • An id at Ready for AI, with docs/plans/<id>.md committed and — for user-facing work — the design mock index. A missing plan → work from the spec/ticket + thread and flag the absence. <ID> uppercase (files, Resolves line); <id> lowercase (branch).

Setup (before any phase)

  1. Detect the integration branch — never assume. Prefer origin/staging if it exists, else git remote show origin | sed -n 's/.*HEAD branch: //p'. Call it INT. Then: git fetch origin (all refs) and git worktree add .worktrees/<ID> -b ai/<id> "$INT". Reusing an existing worktree requires the staleness check: git -C .worktrees/<ID> merge-base --is-ancestor "$INT" HEAD || echo "STALE — rebase in C". WT = the absolute worktree path. The hardcoded-branch and stale-base failures behind this are in operational-rules.md §git.
  2. Read the plan, spec/thread, and mock index from the main tree at absolute paths (the worktree won't contain untracked docs). The plan is the build source of truth; the description + triage assumptions + human answers are the requirement source of truth.
  3. Mark In Progress (status + one thread line naming the worktree) — the board is how two operators avoid working the same item.
  4. Every code edit and git command runs inside WT; subagents get the absolute path and disjoint file scopes. Docs stay in the main tree, never committed onto the branch.
  5. Discover the repo's gates once: its typecheck / codegen / validate / lint / test commands from CLAUDE.md, package scripts, or CI config. These are "the gates" below — the target repo's own, never an assumed toolchain.

Read the full file on GitHub · 287 lines

Files

What ships with it

2 files 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. 1mo ago Changed · -9 lines faae488615cc
  2. 1mo ago First seen · 296 lines · 198 tokens per session scan A bd109183363f

Subscribe to this mod's changes

work is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 198 tokens to every session and 4,435 once invoked, about $0.0008 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 2026-09-04.

Related

Other skills, from other repositories

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

shiplog

Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.

aeonfun/aeon · 46 tokens

connect

Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…

nimbalyst/nimbalyst · 101 tokens

llxprt-issue-workflow

Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…

vybestack/llxprt-code · 88 tokens

cuga-github-issues

Create GitHub issues for cuga-agent (bugs, features, epics, designs, and related work) against origin using gh, with epic → feature → issue hierarchy and GraphQL sub-issue linking. Use when the user says create new issues, report a bug, file a bug, feature request, new feature, create an epic, GitHub issue, sub-issue…

cuga-project/cuga-agent · 88 tokens

implement-issue

Implement a Linear brief in a named GitHub repo. Use when the brief skill is implement-issue or the user wants a new branch and draft PR.

CopilotKit/OpenTag · 35 tokens