difit-resolve

difit-resolve is a skill for Claude Code from TrimVis/skills. It costs 75 tokens per session (2,479 once invoked), scanned A, original, MIT.

A tool for acting on code-review threads recorded in REVIEW.md and optionally syncing them with difit, a browser-based review interface.

In plain words
What is it for?
Read reviewer replies, apply fixes, write responses back to REVIEW.md, and optionally update a running difit session.
Why use it?
It keeps review replies and requested fixes in one source of truth while handling the actual changes.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Good fit Read reviewer replies, apply fixes, write responses back to REVIEW.md, and optionally…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/trimvis/skills/difit-resolve
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 TrimVis/skills --skill difit-resolve
Clone the repo
git clone --depth 1 https://github.com/TrimVis/skills

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 difit-resolve

README.md
[![agentmods](https://agentmods.dev/badge/skills/trimvis/skills/difit-resolve.svg)](https://agentmods.dev/skills/trimvis/skills/difit-resolve)
Your own site
<a href="https://agentmods.dev/skills/trimvis/skills/difit-resolve"><img src="https://agentmods.dev/badge/skills/trimvis/skills/difit-resolve.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,479 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.
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 $0.00075 $0.02479
Opus 5 $0.00037 $0.01239
Sonnet 5 $0.00015 $0.00496
Haiku 4.5 $0.00007 $0.00248

Measured 6d ago against content hash 530cefd85c62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

difit-resolve 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (sync_replies.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

difit-resolve/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Difit Resolve Skill

Read REVIEW.md, pull any new user replies from a running difit (if there is one), apply the fixes, append Claude replies into REVIEW.md, push the augmented state back to difit (if still reachable). REVIEW.md is authoritative — every reply lands in the file. Difit is best-effort: if it's running we sync, if it's not we don't; if it's running but rejects messages we fail loud.

Arguments

  • name (optional, positional): which review to resolve. Default default.
  • --port <port> (optional): difit instance to sync to. If omitted, auto-discover a single running instance.
  • --no-difit (optional): skip the difit sync entirely. Useful when you only want to fix from REVIEW.md without touching the browser session.
  • --commented-only (optional): act only on threads where the user left a reply. Give every other thread status skipped with a one-line reason.

Paths

PROJECT_DIR="$HOME/.claude/projects/$(pwd | sed 's:/:-:g')"
REVIEW_MD="$PROJECT_DIR/reviews/<name>/REVIEW.md"

If REVIEW_MD is missing, error out with Run /difit-review <name> first.

Verified facts about difit (v5.0.1)

  • difit comment get --format json --port <port> reads current state. --port is required (not auto-discovered).
  • difit comment add --type reply is a silent no-op. Always use the frontend POST for replies.
  • POST http://localhost:<port>/api/comments (NO query params) with {threads: [...]} is how replies persist. Returns {"success":true} on a 200.
  • Critical: do not add ?base=<sha>&target=<sha> to the POST URL. difit keys sessions by full SHAs internally, and short SHAs in query params spawn a fresh empty session your write silently lands in — the server still returns {"success":true} and the GET (which uses the active session) shows nothing changed. Omit the query params; the server uses its current selection.
  • difit's session storage is in-memory and lives per (base, target) selection. A fresh --background instance for the same ref reuses its session as long as the process is up.

Read the full file on GitHub · 178 lines

Files

What ships with it

1 file 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.

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. 6d ago First seen · 178 lines · 75 tokens per session scan A 530cefd85c62

Subscribe to this mod's changes

difit-resolve is a skill published in the GitHub repository TrimVis/skills (2 stars, last pushed 23d ago), licensed MIT. It adds 75 tokens to every session and 2,479 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.