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/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.
<a href="https://agentmods.dev/skills/trimvis/skills/difit-resolve"><img src="https://agentmods.dev/badge/skills/trimvis/skills/difit-resolve.svg" alt="Reviewed on agentmods" width="80" 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 5.5 | $0.00030 | $0.00992 |
| Sonnet 5.5 | $0.00015 | $0.00496 |
| Haiku 4.5 | $0.00007 | $0.00248 |
Grade A, and why
difit-resolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Difit Resolve Skill
Read REVIEW.md, pull any new user replies from a running difit (if there is one), apply the fixes, append Claude replies into REVIEW.md, push the augmented state back to difit (if still reachable). REVIEW.md is authoritative — every reply lands in the file. Difit is best-effort: if it's running we sync, if it's not we don't; if it's running but rejects messages we fail loud.
Arguments
name(optional, positional): which review to resolve. Defaultdefault.--port <port>(optional): difit instance to sync to. If omitted, auto-discover a single running instance.--no-difit(optional): skip the difit sync entirely. Useful when you only want to fix fromREVIEW.mdwithout touching the browser session.--commented-only(optional): act only on threads where the user left a reply. Give every other thread statusskippedwith a one-line reason.
Paths
PROJECT_DIR="$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.
- 2mo 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 2mo ago), licensed MIT. It adds 75 tokens to every session and 2,479 once invoked, about $0.0003 per session on Opus 5.5. 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
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…