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 skills add TrimVis/skills --skill difit-resolvegit clone --depth 1 https://github.com/TrimVis/skillsWrote 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.
[](https://agentmods.dev/skills/trimvis/skills/difit-resolve)<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>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.
| Model | Per session | Once 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 | $0.00248 |
Grade A, and why
difit-resolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Difit Resolve Skill
Read REVIEW.md, pull any new user replies from a running difit (if there is one), apply the fixes, append Claude replies into REVIEW.md, push the augmented state back to difit (if still reachable). REVIEW.md is authoritative — every reply lands in the file. Difit is best-effort: if it's running we sync, if it's not we don't; if it's running but rejects messages we fail loud.
Arguments
name(optional, positional): which review to resolve. Defaultdefault.--port <port>(optional): difit instance to sync to. If omitted, auto-discover a single running instance.--no-difit(optional): skip the difit sync entirely. Useful when you only want to fix fromREVIEW.mdwithout touching the browser session.--commented-only(optional): act only on threads where the user left a reply. Give every other thread statusskippedwith a one-line reason.
Paths
PROJECT_DIR="$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.--portis required (not auto-discovered).difit comment add --type replyis 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--backgroundinstance for the same ref reuses its session as long as the process is up.
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.
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.
- 6d ago First seen · 178 lines · 75 tokens per session scan A 530cefd85c62
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.