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/kolodkin/devpowers/shortifynpx skills add kolodkin/devpowers --skill shortifygit clone --depth 1 https://github.com/kolodkin/devpowersWhat 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 | $0.00075 | $0.00853 |
| Opus 5 | $0.00037 | $0.00426 |
| Sonnet 5 | $0.00015 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
shortify 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shortify
Apply as a review pass after writing or editing .md files in subdirectories, or manually via /shortify [file-or-glob].
Scope: Any .md file inside a subdirectory (e.g. docs/, src/), plus code comments and docstrings in source files.
Skip: CLAUDE.md, README.md, CHANGELOG.md, LICENSE.md, and any root-level .md files — these have their own conventions.
Auto vs. manual:
- Markdown triggers automatically as a review pass after
.mdedits in subdirectories. - Code comments & docstrings are manual-only — never auto-triggered by a code edit. Run them on request:
/shortify <file-or-glob>on source files, or when the user opts in for the session ("apply shortify to my comments this session"), after which apply it as a review pass to code you edit for the rest of that session.
Checklist (markdown)
Apply in order:
1. Kill Redundancy
- Remove text that restates what code already shows — link to the source instead.
- One example per concept. Delete duplicates.
- Merge overlapping sections — keep the clearer one.
2. Cut Wordiness
- Replace wordy phrases: "In order to" -> "To", "It is important to note that" -> delete, "This allows you to" -> delete or rephrase.
- Remove filler sentences that add no information.
- Prefer bullet lists over paragraphs for reference material.
3. Tighten Structure
- Delete empty/trivial sections. Merge one-sentence sections into neighbors.
- Shorten introductions — title + one sentence is enough.
- Flatten heading depth:
#and##only. Avoid###and deeper — restructure instead.
4. Reference Code, Don't Duplicate
- Replace inline implementations with references:
See DataContext.query() in aaiclick/data/data_context.py. - Keep short usage examples (3-5 lines). Delete long inline code.
- API docs: call signature + one example, not internals.
5. Preserve
- Content with no other source (design decisions, rationale, gotchas).
- Non-obvious usage examples and genuine
!!! warningadmonitions. - Do NOT change referenced code — only the surrounding text.
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.
- yesterday First seen · 77 lines · 75 tokens per session scan A 5ce8584ebe25
shortify is a skill published in the GitHub repository kolodkin/devpowers (2 stars, last pushed 23d ago), licensed MIT. It adds 75 tokens to every session and 853 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…