A task-board synchronizer that prepares a board's tasks for search and review by a remote service. It identifies the repository and branch before starting the synchronization.

Use it when you need to sync or index tasks from a configured board for a repository and selected branch.

It keeps the review system's task index aligned with the configured board without requiring the client to list tasks or handle credentials.

sync-tasks — Skill by mimfort

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 skills/mimfort/rag_for_git/sync-tasks

Any agent

npx skills add mimfort/rag_for_git --skill sync-tasks

Clone the repo

git clone --depth 1 https://github.com/mimfort/rag_for_git

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 623 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00036	$0.00623
Opus 5	$0.00018	$0.00311
Sonnet 5	$0.00007	$0.00125
Haiku 4.5	$0.00004	$0.00062

Measured 2d ago against content hash 62343d6f92e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-tasks 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 2d 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.

plugin/skills/sync-tasks/SKILL.md · 48 lines

What it actually says

Sync Tasks

Reply in Russian. This is a thin, server-side trigger: the server enumerates, normalizes, and indexes the board. Do not enumerate tasks in the client and do not send credentials.

Resolve the repository path with git rev-parse --show-toplevel, then run git -C <path> remote get-url origin. For HTTPS and SSH URLs, remove the scheme, userinfo, and host; for scp-style remotes, remove everything through the host's first colon. Preserve every path segment after the host or scp colon, remove the leading slash, strip a trailing .git, then lowercase and validate the result as the canonical lowercase repository id (owner/name or group/.../name). Examples:
- https://gitlab.example.com/group/sub/repo.git → group/sub/repo
- ssh://[email protected]/group/sub/repo.git → group/sub/repo
- [email protected]:group/sub/repo.git → group/sub/repo
If origin is missing or ambiguous, ask for the complete namespace/repo id; do not guess from the directory name.
Resolve branch independently. Pass a non-null branch only when the user explicitly supplied or selected one and it is in the tracked branches list (REVIEW_BRANCHES). With no explicit tracked selection, pass branch=null so the server uses its primary tracked branch. Never infer the branch from the current worktree branch or blindly pass an untracked feature branch.

Call only repo mode with operation flags. The server owns effective board-policy resolution; do not reconstruct policy in the client:

sync_board(repo=<canonical owner/name or group/.../name>,
           branch=<explicit tracked branch or null>,
           limit=<limit or null>,
           purge_orphaned=<explicit request or false>,
           keep_with_prs=<explicit request or true>,
           force_renormalize=<explicit request or false>)

If the result is a configuration or policy error, explain it in Russian and stop. Do not retry through unfiltered explicit mode: that could enumerate or purge the wrong task corpus.
Report the server-side summary in Russian, including eligible, filtered_by_age, filtered_archived, age_unknown, archive_unknown, filter_applied, filter_fingerprint, filter_source, by_board, purge, and warnings. Explain warnings and leave the local repository unchanged.

sync_board is idempotent: rerunning is safe and inexpensive when the watermark is warm. It reads the board; it never writes back.

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.

2d ago First seen · 48 lines · 36 tokens per session scan A 62343d6f92e8

Subscribe to this mod's changes

sync-tasks is a skill published in the GitHub repository mimfort/rag_for_git (21 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 623 once invoked, about $0.0002 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.

Code review Data and AI Git and workflow ai claude-code code-graph developer-tools mcp

graft

This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.

trailhq/Graft · 56 tokens

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

code-graph

This skill should be used when understanding code structure, finding dependencies between functions/classes, tracing call graphs, or exploring code relationships. Trigger phrases include 'code graph', 'call graph', 'who calls', 'what calls', 'find dependencies', 'code structure', 'inheritance', 'find paths'.

FalkorDB/code-graph · 64 tokens

agentmap

Use for TypeScript/JavaScript codebase navigation — symbol lookup, blast radius, reuse checks, and repo orientation. Prefer agentmap before serial grep when exploring imports, exports, or where a symbol lives. Package is @raymondchins/agentmap (not the unrelated npm package agentmap).

raymondchins/agentmap · 64 tokens

m1nd-operator

Use when the user mentions m1nd or when repo investigation, search, review, docs/spec work, or risky change prep should go through m1nd first before grep, glob, or manual file reads. Covers m1nd-first routing, L1GHT and universal document ingestion, risky edit preparation, document-to-code binding, the served owner +…

maxkle1nz/m1nd · 111 tokens

m1nd-first

Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…

maxkle1nz/m1nd · 78 tokens