fledgeling-co

68 mods across 8 repositories, 3 stars between them.

fledgeling-co/fledgeling-plugins

Instructions file

Claude Code instructions for fledgeling-co/fledgeling-plugins, covering claude.md, adding or renaming a plugin — four places, one commit, the root readme row has a shape, and it breaks quietly, adding a plugin now also drafts an email and the site indexes this repo — there is no fifth registration.

2 yesterday A 2,424 tokens original MIT

agent-voice

03

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Give agent-authored text a real voice: the prose an agent emits inside Claude Code and other harnesses. Seven registers (terminal reply, work report, commit and PR, review comment, written document, SKILL.md and instruction file, subagent brief), a deterministic lint that hard-fails closing flourishes…

2 yesterday A tokens not measured original MIT

agent-voice

04

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Give agent-authored text a real voice: the prose an agent emits inside Claude Code and other harnesses. Routes to one of seven registers — terminal reply, work report, commit and PR, review comment, written document, SKILL.md and instruction file, subagent brief — then drafts or revises against evidence-anchored rules…

2 yesterday A 257 tokens original MIT

anvil-errand

05

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Send a Claude Code agent to work in a container on another machine through Anvil, using the single anvil errand verb, and read its refusals correctly when a piece of the path is missing. Covers the whole loop — check the preconditions, start the errand, watch it, stop it — and translates each stable refusal kind (err.

2 yesterday A tokens not measured original MIT

anvil-errand

06

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Send a Claude Code agent to work in a container on another machine through Anvil, using the single anvil errand verb, and read its refusals correctly when a piece of the path is missing. Covers the whole loop — check the preconditions, start the errand, watch it, stop it — and translates each stable refusal kind…

2 yesterday A 232 tokens original MIT

armada-sync

07

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Keep the portfolio manifest /Dev/ARMADA.md truthful after working in any /Dev project. Surgical, single-entry updates: status, features, key-file references, updated stamp, index row, one changelog line. The counterpart maintenance skill to ship-armada — every project's CLAUDE.md points here so the manifest stays fre.

2 yesterday A tokens not measured original MIT

atlas-publish

08

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Takes the open PRs of the Atlas/Bella monorepo to a registered draft release on either the over-the-air or the App Store lane, classifying between them from the expo-updates native fingerprint rather than from intent — ios.buildNumber sits inside that fingerprint, so a buildNumber bump alone forces a store release.…

2 yesterday A tokens not measured original MIT

atlas-publish

09

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Atlas/Bella release conductor — take the open PRs to a registered draft release, on the OTA lane or the App Store lane. Use when someone wants Atlas work in front of users: "ship an Atlas release", "publish an OTA update", "release the app", "cut a new Atlas build", "push a JS-only update to users", "do a full App…

2 yesterday A 280 tokens original MIT

be-my-witness

10

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Validate a UI screenshot against what a test expected and against a design mock, returning a pass/fail gate plus severity-ranked findings. Runs a deterministic pre-scan first (is this evidence, did the surface settle, are the two framings even comparable), crops and zooms rather than judging a full-page thumbnail…

2 yesterday A tokens not measured original MIT

be-my-witness

11

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Validate a UI screenshot against what a test expected and against a design mock, and return both a pass/fail gate and severity-ranked findings. Use whenever a test, capture suite, or review step has produced a screenshot that something now has to judge — "does this screenshot match the expected output", "does the…

2 yesterday A 155 tokens original MIT

better-goal

12

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Hold a long autonomous run to a finish line using command hooks and a stall watcher this skill creates itself, rather than the built-in /goal. /goal is a prompt Stop hook judged by a small model on transcript text alone, so it grades what the run said rather than what is true, and Claude Code overrides any Stop hook…

2 yesterday A tokens not measured original MIT

better-goal

13

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Hold a long autonomous run to a finish line using a Stop guard and a stall watcher this skill creates itself, with no dependence on the /goal command. Use when someone wants a run that keeps going until the work is actually done — "set a goal to ship the rest of the backlog", "keep going until every item is complete"…

2 yesterday A 357 tokens original MIT

better-loop

14

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Arm recurring or event-driven work as a change-gated watcher this skill creates itself, so a tick fires only when something has actually changed. A scheduled loop re-sends the same unmet condition and the same failing tasks turn after turn, re-billing the session's whole prefix each time: five of twelve measured heavy.

2 yesterday A tokens not measured original MIT

better-loop

15

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Arm recurring or event-driven work as a change-gated watcher this skill creates itself, so a tick fires only when something has actually changed. Use when someone wants work that keeps running — "loop on this", "keep checking the deploy", "monitor the benchmark runs and fix errors", "create a loop prompt", "harden…

2 yesterday A 298 tokens original MIT

braindump

16

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Write a context-compaction summary that survives being the only thing the next session has, and prove it against the transcript it replaced and against Claude Code's own /compact. Use this whenever someone is about to run /compact, asks what to keep before compacting, wants to hand a long session off to a fresh one…

2 yesterday A 168 tokens original MIT

clarify

17

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Decide whether to interrupt the user with a question, then ask it so it takes one click to answer. Sweeps the conversation, the repo and earlier agent output for the answer, kills questions whose answer would not change the work, then refers every surviving technical fork to another model family before the user sees…

2 yesterday A tokens not measured original MIT

clarify

18

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Decide whether to interrupt the user with a question, then ask it so it takes one click to answer. Use this whenever you are about to ask the user something mid-task, when you hit a fork with several defensible answers, when a request is ambiguous enough that two readings would produce different work, before anything…

2 yesterday A 307 tokens original MIT

code-review

19

fledgeling-co/fledgeling-plugins

Plugin Claude Code

A diff review that reports what it could not check. Finds with fourteen named angles that are forbidden from suppressing each other, so two reasons for flagging one line both survive to be judged; verifies with three verdicts, where realistic-but-unproven stays in as PLAUSIBLE rather than being dropped with the noise.

2 yesterday A tokens not measured original MIT

code-review

20

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Review a diff, a PR, or a branch range and report findings — correctness bugs first, then reuse, simplification, efficiency, altitude and convention breaches. Use when the user asks for a code review, asks to "review my changes / PR / diff / branch", asks for a security, performance, dead-code, test-coverage…

2 yesterday B 349 tokens original MIT

create-luke-content

21

fledgeling-co/fledgeling-plugins

Plugin Claude Code

Write anything in Luke Rhodes' voice, with a copywriting craft layer under the marketing route rather than a voice layer on its own. Routes a request to one of six personas (LinkedIn post and long-form article, marketing content, code review, Slack and chat, short-form, ADHD and book audience), draws the base voice…

2 yesterday A tokens not measured original MIT

create-luke-content

22

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Write any content in Luke Rhodes' authentic voice (Diolog CTO and co-founder), routed through the right persona variant: LinkedIn posts and long-form blog articles, marketing content (announcements, release notes, launch/landing copy, campaign emails), code reviews, Slack/chat messages, short-form content (tweets/X…

2 yesterday A 232 tokens original MIT

create-luke-content

23

fledgeling-co/fledgeling-plugins

Skill Claude CodeCodex

Write any content in Luke Rhodes' authentic voice (Diolog CTO and co-founder), routed through the right persona variant: LinkedIn posts and long-form blog articles (with graphic concept), marketing content (announcements, release notes, landing copy, campaign emails), code reviews, Slack/chat messages, short-form…

2 yesterday A 228 tokens original MIT

create-mac-icon

24

fledgeling-co/fledgeling-plugins

Plugin Claude Code

macOS app icon creation with a measured fidelity loop: direction catalogue from a 532-icon corpus, three generation engines (hand-authored layered SVG, Arrow vector, corpus-referenced raster), a written audit.html contact sheet, and a multi-scale scoring harness that iterates the SVG master against the winning raster…

2 yesterday A tokens not measured original MIT