A workflow for reviewing and fixing confirmed findings from legitAgent, a heuristic scanner. It scans a specified workspace, applies only confirmed fixes, and scans again.

Use it to scan a workspace, review findings, fix items marked for confirmation, repeat the checks, and show cases that need human judgment. It is not a legal opinion.

It prevents suspected or rejected findings from being changed accidentally and checks whether serious confirmed findings remain after repairs.

fix — Skill for Cursor by kiruxich/legitAgent

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 kiruxich/legitAgent --skill fix

Clone the repo

git clone --depth 1 https://github.com/kiruxich/legitAgent

Made for: Cursor.

Or install legitagent, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kiruxich/legitagent/fix/github.svg)](https://agentmods.dev/skills/kiruxich/legitagent/fix)

Your own site

<a href="https://agentmods.dev/skills/kiruxich/legitagent/fix"><img src="https://agentmods.dev/badge/skills/kiruxich/legitagent/fix/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kiruxich/legitagent/fix"><img src="https://agentmods.dev/badge/skills/kiruxich/legitagent/fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 336 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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00336
Opus 5.5	$0.00016	$0.00134
Sonnet 5.5	$0.00008	$0.00067
Haiku 4.5	$0.00004	$0.00034

Measured 2mo ago against content hash 6f7eb947212a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fix 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.

skills/fix/SKILL.md · 16 lines

What it actually says

Fix

Вызови MCP scan сервера legitagent. Всегда передай абсолютный root открытого workspace (или путь пользователя).
Вызови MCP review с тем же контекстом. Offline-review возвращает not_reviewed: такую находку, как и ask_human, нельзя автоматически считать подтверждённой.
Вызови MCP autofix с write: false. Покажи safe и manual recipes. write: true применяет все safe-рецепты свежего scan, а не только LLM-confirm, поэтому перед записью проверь preview и не применяй его при неоднозначных находках.
Только в рамках явной команды пользователя /fix и после проверки preview передай write: true. У autofix нет per-finding фильтра: если preview содержит reject, ask_human или not_reviewed, не используй write: true; manual recipes оставь человеку.
После правок снова scan + review. Повторяй, пока не останется confirm с severity: high, если пользователь явно не принял риск.
Покажи человеку все ask_human и not_reviewed. Напомни: это эвристика, не юридическое заключение.

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.

2mo ago Changed 6f7eb947212a
2mo ago First seen · 16 lines · 41 tokens per session scan A f299297f6579

Subscribe to this mod's changes

fix is a skill published in the GitHub repository kiruxich/legitAgent (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 336 once invoked, about $0.0002 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.

Security cli compliance cursor linter mcp mcp-server

fix next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fixkiruxich/legitAgent	Skill	2	2mo ago	MIT	A	41	Cursor
pipefy-toolkit-setuppipefy/ai-toolkit	Skill	53	yesterday	Apache-2.0	A	86	Claude Code
mcpmgetmcpm/cli	Skill	3	yesterday	MIT	A	38	Claude Code, Codex
inertgetmcpm/cli	Skill	3	yesterday	MIT	A	13	Claude Code
release-notesxyiqq/skilldoctor	Skill	11	2mo ago	MIT	A	37	Claude Code, Codex
reviewgetmcpm/cli	Skill	3	yesterday	MIT	A	6	Claude Code, Codex
requirements-authoringgriddynamics/rosetta	Skill	375	today	Apache-2.0	A	0	Claude Code