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/dhananjay625/dev-workflow/workflownpx skills add Dhananjay625/dev-workflow --skill workflowgit clone --depth 1 https://github.com/Dhananjay625/dev-workflowWhat 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 | $0.01988 |
| Opus 5 | $0.00044 | $0.00994 |
| Sonnet 5 | $0.00018 | $0.00398 |
| Haiku 4.5 | $0.00009 | $0.00199 |
Grade A, and why
workflow 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development workflow
Follow these phases in order. Skip Phase 0 only for trivial tasks (<~20 lines, obvious approach, no schema/pipeline impact).
Session continuity (do this first, every session)
- FIRST ACTION: locate the project's
CHANGELOG.md. Check the session root first, then search downward (e.g.find . -maxdepth 3 -name CHANGELOG.mdexcluding node_modules/.git). In a monorepo, the changelog in the directory containing the files being edited is the project's memory - never create a second changelog at a higher level, which would split it. Once located, read it: its## Current stateblock says exactly where the last session stopped - resume from it; never re-explore what it already answers. - If
CHANGELOG.mddoes not exist, create it from this skill'stemplates/CHANGELOG.template.mdbefore other work. - If it exists but has NO
## Current stateblock (common on existing repos), PREPEND the block from the template above the existing content; never rewrite or truncate existing history. - Log every change in the same turn it is made:
file:line - before->after - why - verified how. Never batch entries. - Before ANY session ends (including blocked/interrupted): rewrite
## Current stateso a fresh session with zero memory can continue from it alone: what works (with proof command), what's broken (file:line + symptom), exact next step, open decisions, known dead ends (DO NOT list). Respect the DO NOT list: recorded dead ends are never retried.
Phase 0 - Plan
Explore read-only. The plan must contain these five items:
- Objective (one sentence)
- Deliverable (exact file paths that will exist when done)
- Approach (key decisions + one rejected alternative if non-obvious)
- Risks/blockers (surface now, not mid-build)
- Delegation (which specialist roles, if any, what each returns, and the estimated cost tradeoff) If the harness has a fuller native plan format, use it - these five items are the required core, not a cap.
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.
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 · 156 lines · 89 tokens per session scan A 904adc92ed6d
workflow is a skill published in the GitHub repository Dhananjay625/dev-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 89 tokens to every session and 1,988 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…