amend

amend is a skill for Claude Code from juicesharp/rpiv-mono. It costs 101 tokens per session (1,865 once invoked), scanned A, original, MIT.

A focused document reviser that updates one research paper, plan, or other document using the findings marked as failed by a grading process.

In plain words
What is it for?
Use it to apply cited feedback to a document and send the revised version back for grading.
Why use it?
It fixes the specific problems identified by the graders without rewriting parts that already pass or expanding the document’s scope.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit Use it to apply cited feedback to a document and send the revised version back for grading.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juicesharp/rpiv-mono/amend
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.

Any agent
npx skills add juicesharp/rpiv-mono --skill amend
Clone the repo
git clone --depth 1 https://github.com/juicesharp/rpiv-mono

Made for: Claude Code.

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 amend

README.md
[![agentmods](https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/amend/github.svg)](https://agentmods.dev/skills/juicesharp/rpiv-mono/amend)
Your own site
<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/amend"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/amend/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for amend

Your own site · 80×15
<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/amend"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/amend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00101 $0.01865
Opus 5 $0.00051 $0.00932
Sonnet 5 $0.00020 $0.00373
Haiku 4.5 $0.00010 $0.00186

Measured 7d ago against content hash e91851d95369, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

amend 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 7d 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.

packages/rpiv-pi/skills/amend/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amend

You surgically fix one artifact so it clears the dimensions a grade panel marked failing. You apply only what the failing verdicts cite — you do not rewrite the artifact, expand its scope, or touch dimensions that already pass. One pass, non-interactive. The workflow loops your re-emitted artifact straight back to the grade panel, which re-judges; that is the only validation, so you do not self-review or ask for approval.

Input

$ARGUMENTS — flags the orchestrator wires from the gate's channels. Parse them generically, agnostic to the channel name:

  • Verdicts — every flag whose name ends in -verdicts (e.g. --research-verdicts, --plan-verdicts), repeatable. Each value is a verdict JSON path.
  • Citation floors — every flag whose name ends in -cite-check (e.g. --plan-cite-check, --code-cite-check), repeatable. Each value is a cite-check verdict JSON path.
  • Lineage sources — the read-only context flags --goal, --research, and --subplans (repeatable; build's fix arms only). --goal is the verbatim brief, --research the architecture/precedent findings, --subplans the per-cluster sub-plans. They are context, never the artifact to re-emit.
  • Artifact — the single remaining --<channel> flag that is not a verdicts, citation-floor, or lineage-source flag (i.e. not ending in -verdicts or -cite-check, and not --goal/--research/--subplans). Its value is the artifact to fix and re-emit; for both build fix arms this resolves to --plans.

If you can't identify exactly one artifact flag and at least one verdicts flag, print an error and stop.

Metadata

node "${SKILL_DIR}/../_shared/now.mjs"

The first tab-separated field is <iso> (use as last_updated).

Steps

  1. Read the artifact fully (no limit/offset) and read every verdict JSON.
  2. Select the failing findings. Group verdicts by dimension; for each dimension keep the latest (by graded_at) — verdicts accumulate across amend loops, so an older failing verdict may already be superseded. From the latest-per-dimension set, take those with pass: false, and also any carrying a non-empty risk_duty_demotions array (a field the workflow stamps after grading — even when the verdict's own pass is true, a demoted risk ruling records the demotion there). Additionally, from each PASSING dimension's latest verdict, select any finding that asserts a deterministic failure-as-written — the emitted code or edit fails typecheck/compile as written, a cited file or symbol does not exist, an edit anchor does not match its target. Left in place, such a finding is a landmine: a later round's grader will rate it blocking and it then costs a whole extra grade-fix lap. Select only that class from passing verdicts — every other finding on a passing verdict stays out of scope. If this selects nothing, the artifact already passes: re-emit it unchanged (only bump last_updated) and report — the panel will confirm.
  3. Apply each selected verdict's feedback/findings surgically (for a passing verdict, only its selected failure-as-written findings — its feedback is not an instruction set). Use each finding's where to locate the exact spot and change only that. Honor feedback as the instruction set. Where a finding requires checking the codebase (a correctness or pattern-following fix), Read/Grep the cited file:line to ground the edit — but never edit code, only the artifact. A completeness-class finding (the artifact under-covers the brief) is repaired from the lineage sources — --goal, --research, --subplans — by reading the authoritative source there and folding the missing point in; never reconstruct the missing content from verdict prose or guess it from a directory listing.
  4. Confirm coverage — every selected finding maps to an edit you made. Do not introduce changes no finding asked for.
  5. Re-emit the artifact to the SAME path (Edit in place; Write only if a structural rewrite of a section is unavoidable). Preserve everything outside the cited findings, keep status: ready, and update last_updated: <iso> in the frontmatter. Same path ⇒ the artifact's channel updates latest-wins for re-judging.
  6. Print the artifact path, then a one-line summary: amended for <dimensions>: <k> findings addressed.

Read the full file on GitHub · 53 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. 7d ago Changed e91851d95369
  2. 11d ago First seen · 53 lines · 101 tokens per session scan A 7742f43608f9

Subscribe to this mod's changes

amend is a skill published in the GitHub repository juicesharp/rpiv-mono (779 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,865 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens