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/initialneil/project-with-reflect/releasenpx skills add initialneil/project-with-reflect --skill releasegit clone --depth 1 https://github.com/initialneil/project-with-reflectWhat 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 | $0.00089 | $0.00731 |
| Opus 5 | $0.00044 | $0.00365 |
| Sonnet 5 | $0.00018 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
release 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release — ship a new project-with-reflect version
One command for the whole pipeline: publish → refresh the local install, so the
loop is edit the skill → /release.
Usage
/release [patch|minor|major | X.Y.Z] ["one-line changelog note"]
Version-bump map (this project's convention):
- major — a user-facing big / breaking change → bumps the first number.
- minor — a major fix → bumps the middle number.
- patch — a minor fix → bumps the last number. (default)
- An explicit
X.Y.Zis also accepted.
The note becomes the CHANGELOG entry. If omitted, summarize what changed in the plugin since the last tag in one line — don't invent a generic message.
Steps
- Locate the repo. Work from the repo root (the dir with
.claude-plugin/plugin.jsonandscripts/publish.sh). If the CWD isn't it,cdto~/Playground/vibe_coding/project-with-reflect. - Preflight (report, don't nag).
git statusto show what's being released; confirm you're onmain. Echo one line:releasing vCUR → vNEXT — <note>. The user typing/releaseIS the go-ahead — don't prompt again. - Publish. Run
scripts/publish.sh <bump-or-version> "<note>". It bumps the version in both manifests, prepends the CHANGELOG, commits, tagsv<version>, pushes, and (ifghis present) cuts a GitHub release. - Refresh this machine's install. If installed via the marketplace, run
claude plugin marketplace update project-with-reflect. If installed via the user-scope symlink (~/.claude/skills/project-with-reflect→ this repo), it's already live — nothing to do. - Report. Print the new version + tag, and remind that other users update with
/plugin update project-with-reflect.
Guardrails
/releasepushes a public tag. Run it only when the user invoked/release— never speculatively, never as a side effect of another task.- If
scripts/publish.shfails (push rejected, tag exists, bad version), STOP and report the exact failure. Don't force-push or re-tag without asking. - A release is for plugin/skill changes only — README / tooling / CI edits are a
plain
git commit+git push, not/release. - Don't edit skill content here —
/releaseships what's already committed.
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.
- 2d ago First seen · 56 lines · 89 tokens per session scan A 410696f9426d
release is a skill published in the GitHub repository initialneil/project-with-reflect (13 stars, last pushed 14d ago), licensed MIT. It adds 89 tokens to every session and 731 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…