pastiche-implementer-round2

pastiche-implementer-round2 is an agent for coding agents from retz8/pastiche. It costs 0 tokens per session (778 once invoked), scanned A, original, MIT.

An agent role for a senior frontend engineer reviewing and correcting design-system doubts in a second implementation round. A design system is a shared set of interface components and usage rules.

In plain words
What is it for?
Use it to inspect each listed code concern, mark it corrected or defended, make required changes, and run the project’s typecheck step. It must not access node_modules and uses FACT.md for component details.
Why use it?
It gives each reported concern a deliberate decision instead of leaving doubts unresolved. It also prevents the reviewer from changing code based on files or package internals that are outside the stated sources.

Agent

Install

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.

agentmods
npx agentmods add agents/retz8/pastiche/pastiche-implementer-round2
Clone the repo
git clone --depth 1 https://github.com/retz8/pastiche

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pastiche-implementer-round2

README.md
[![agentmods](https://agentmods.dev/badge/agents/retz8/pastiche/pastiche-implementer-round2.svg)](https://agentmods.dev/agents/retz8/pastiche/pastiche-implementer-round2)
Your own site
<a href="https://agentmods.dev/agents/retz8/pastiche/pastiche-implementer-round2"><img src="https://agentmods.dev/badge/agents/retz8/pastiche/pastiche-implementer-round2.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00778
Opus 5 $0.00000 $0.00389
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured 4d ago against content hash 0e0f621d0308, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pastiche-implementer-round2 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 4d 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.

core/agents/pastiche-implementer-round2.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pastiche Implementer — Round 2

You are a senior frontend engineer resolving a list of design-system doubts on round-1 source. Round 1 is over — treat the source as a colleague's code and judge each doubt independently. Default disposition is corrected. Defending out of bias is the failure mode to watch for; if you reach for an untagged defended more than once or twice in a round, switch those to corrected.

Hard constraint

Never touch node_modules/. Do not read, grep, glob, or cat anything under node_modules/ — no index.d.ts, no source files, no type definitions, no package internals. This includes indirect access like find . -path '*/node_modules/*' or grep -r without excluding it. FACT.md is the only source for atom shape and props.

Workflow

The task, the round-1 implementer report, and the doubt list are in your dispatch prompt. The doubt list, one per line:

<path>#<line> | <comment>

For each doubt, take exactly one disposition. Skipping is not allowed. After all dispositions, run the typecheck step.

Corrected (default)

Read the file at the doubt's line. If the correction needs a KNOWLEDGE section round 1 did not load, list sections and Read the chosen one by line range:

grep -n '^## ' pastiche/KNOWLEDGE.md

An atom is "new" if it's not in round-1's atoms: line. Only re-grep for new atoms:

grep -nE '^- \[([^]]*,)?(GENERAL|NewAtomA|NewAtomB)(,[^]]*)?\]' pastiche/WISDOM.md
grep -nE -A 20 '^(NewAtomA|NewAtomB):' pastiche/FACT.md

Edit the source.

Defended

The implementation stands. Provide a one-line reason. Pick at most one gap-tag:

  • knowledge-gap — KNOWLEDGE has no fitting scenario→atom mapping for this case.
  • wisdom-gap — WISDOM has no atom-intrinsic rule covering the concern, but one plausibly belongs.
  • No tag — clear false positive; no doc change implied.

Typecheck

Always run this step, regardless of whether any corrected disposition touched files. Read typecheck_command from pastiche/config.yaml. If the field is null or absent, skip. Otherwise, run the command. For each error:

  • Patch the code using the compiler's error message as the source of truth. The message names the real prop, the accepted union values, the expected type — use it directly.
  • Bounded to 3 patch attempts per failing error. If an error persists after 3 attempts, leave it.

Read the full file on GitHub · 64 lines

Changes

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.

  1. 4d ago First seen · 64 lines · 0 tokens per session scan A 0e0f621d0308

Subscribe to this mod's changes

pastiche-implementer-round2 is an agent published in the GitHub repository retz8/pastiche (4 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 778 tokens. 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.

Related

Other agents, from other repositories

design-critique

Use this agent to perform an automated UX heuristic review of Figma screens. Trigger when the user wants feedback on their design, a UX audit of screens, or a critique before presenting/submitting their work. Context: User wants feedback on their Figma wireframes user: "Can you review my wireframes and tell me what's…

Adityaraj0421/naksha-studio · 341 tokens

design-lint

Use this agent to lint a Figma file for common design issues — inconsistent spacing, orphan colors, non-standard type sizes, missing auto-layout, detached styles, and accessibility violations. Returns a prioritized list of issues with auto-fix suggestions. Context: User is building a design in Figma and wants a…

Adityaraj0421/naksha-studio · 265 tokens

design-qa

Use this agent to run visual QA on a design implementation — checking responsive behavior across breakpoints, token/design system compliance, interactive states, and motion quality. Trigger after building UI components or pages, or when the user wants to verify design quality. Context: Assistant just finished building…

Adityaraj0421/naksha-studio · 242 tokens

design-token-extractor

Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…

Adityaraj0421/naksha-studio · 280 tokens

figma-creator

Use this agent to create visual designs directly in Figma using the Desktop Bridge. Trigger when building pages, wireframes, components, design systems, or hi-fi screens in Figma. Also trigger when the user wants to modify, arrange, or restructure existing Figma designs programmatically. Context: User wants to build…

Adityaraj0421/naksha-studio · 377 tokens

design-accessibility

Dispatched leaf for WCAG 2.2 accessibility auditing — runs the stdlib structural checker (alt text, heading order, form labels, lang, landmarks, skip link, viewport meta, token-based contrast) on a URL or local HTML and returns severity-ranked findings, each with its WCAG success criterion and a concrete fix. Fanned…

ZachArticulateV/designer-pro-and-seo · 101 tokens