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/shivaedev/pardes/implement-changenpx skills add ShivaeDev/pardes --skill implement-changegit clone --depth 1 https://github.com/ShivaeDev/pardesWhat 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 | $0.00028 | $0.00509 |
| Opus 5 | $0.00014 | $0.00254 |
| Sonnet 5 | $0.00006 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
implement-change 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Change
Execute an approved PR goal while keeping the primary session responsible for coordination. The manager never edits code. Every PR has one owner worker in a managed worktree.
Entry Gate
Confirm that the PR is inside the user-approved scope and sequence. For a standalone implementation request, the explicit request is the approved scope.
Read references/worktree-workers.md before dispatching a writing worker.
Dispatch
- Create a linked worktree for the owner worker with
scripts/manage_worker_worktree.py. Run the helper outside the sandbox from the outset. Use an explicit branch-point SHA. - Give the owner the approved PR goal and boundaries. The owner inspects the code, forms the implementation plan, edits, runs repo-supported validation, creates normal commits, and reports commit SHAs, changed paths, validation, and surprises.
- Spawn supporting workers in separate managed worktrees when independent chunks can proceed in parallel. Supporting workers commit their chunks; the owner worker integrates accepted support commits.
- Keep the owner available for verifier, CI, and review feedback.
Keep each active worker branch on its assigned branch-point SHA. Do not rebase or recreate it merely because the target branch advanced. Refresh only for a real dependency, conflict, or identified semantic overlap.
Do not manually delete branches or worktrees after a PR. Worktree creation quietly reaps clean managed worktrees whose tip commit is older than seven days.
Wait for Workers
- Continue useful non-overlapping manager work after dispatch.
- Once worker output is the actual blocker, call
wait_agentwith all unresolved worker IDs and a900000ms timeout. Use a longer timeout, up to the API maximum, when the assigned task reasonably needs it. - Treat an ordinary timeout as "still working", not as a progress event. Do not narrate or create short-poll loops. Wait again with a long timeout unless there is evidence the worker is stuck or the user asks for status.
What ships with it
4 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 · 56 lines · 28 tokens per session scan A 825977877c78
implement-change is a skill published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 509 once invoked, about $0.0001 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…