remediate CLAUDE.md

remediate CLAUDE.md is an instructions file for coding agents from fvckprth/remediate. It costs 1,842 tokens per session, scanned A, original, MIT.

Repository instructions for Remediate, including the required format for issue tickets in Linear, a project-management tool.

In plain words
What is it for?
Creating bug, feature, or improvement tickets with the project’s required title prefixes, screenshots, labels, status, priority, and assignment rules.
Why use it?
They prevent tickets from missing required fields or using inconsistent titles, labels, statuses, priorities, and project assignments.

Instructions file

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 instructions/fvckprth/remediate/claude-md
Clone the repo
git clone --depth 1 https://github.com/fvckprth/remediate

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 remediate CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fvckprth/remediate/claude-md.svg)](https://agentmods.dev/instructions/fvckprth/remediate/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fvckprth/remediate/claude-md"><img src="https://agentmods.dev/badge/instructions/fvckprth/remediate/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,842 This file is loaded in full into every session.
When invoked 1,842 The same file — it is already loaded in full.
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 $0.01842 $0.01842
Opus 5 $0.00921 $0.00921
Sonnet 5 $0.00368 $0.00368
Haiku 4.5 $0.00184 $0.00184

Measured 3d ago against content hash b4ed88a561a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remediate CLAUDE.md 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 3d 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.

CLAUDE.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remediate — Claude Code Instructions

Linear ticket format

When creating Linear tickets for this project, follow this spec exactly. Both Parth and his collaborator use this format.

How tickets are created

  • Claude creates tickets directly via the Linear MCP (claude mcp add --transport sse linear https://mcp.linear.app/sse)
  • Screenshots are captured via Chrome DevTools MCP, saved locally, and the local path is noted in the ticket body for manual drag-drop into Linear

Fields (always set)

Field Rule
Title lowercase, human-readable, area prefix required
Label exactly one of Bug, Feature, Improvement (case matches Linear workspace)
Status Backlog
Priority always assigned (see rubric)
Project match an existing Linear project if relevant, otherwise leave blank
Assignee decided per-ticket (do not auto-assign)

Title prefixes

Pick one based on the primary area changed. Multi-area tickets use the primary area's prefix. If nothing fits, use misc:.

  • widget: — embedded feedback widget (toolbar, panels, capture flow)
  • capture: — screenshot, video, audio, area selector
  • annotate: — annotation markers, popovers, highlighting
  • notes: — voice panel, text note panel
  • review: — review panel / submission flow
  • server: — server-side parsing, API routes
  • integrations: — linear, slack, github, email, webhook
  • infra: — build, deploy, env, tsup config
  • repo: — cross-cutting cleanup, tooling, CI
  • skill: — agent skill (SKILL.md)
  • misc: — nothing else fits

Examples:

  • widget: voice notes don't save offline
  • integrations: linear ticket missing priority
  • capture: video recording freezes on safari

Priority rubric

  • Urgent — blocks the Linear project/milestone the ticket lives in
  • High — needed soon after launch, or a significant bug affecting most users
  • Normal — real improvement or bug, but launch ships fine without it (Linear calls this "Normal", priority value 3)
  • Low — nice-to-have, nitpick, backlog-forever candidate

Read the full file on GitHub · 190 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. 3d ago First seen · 190 lines · 1,842 tokens per session scan A b4ed88a561a1

Subscribe to this mod's changes

remediate CLAUDE.md is an instructions file published in the GitHub repository fvckprth/remediate (11 stars, last pushed 3mo ago), licensed MIT. It adds 1,842 tokens to every session, about $0.0092 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.