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 synaptiai/synapti-marketplace --skill branch-and-task-managementgit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/branch-and-task-management)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/branch-and-task-management"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/branch-and-task-management/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/synaptiai/synapti-marketplace/branch-and-task-management"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/branch-and-task-management.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 | $0.00060 | $0.00805 |
| Opus 5 | $0.00030 | $0.00402 |
| Sonnet 5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
branch-and-task-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Branch and Task Management
Contract
Iron law: no code before context — read the issue body and comments, load history, understand scope, then create the branch. Invoked by /flow:start (Phase 1 EXPLORE through Phase 2 PLAN) and by the implementation-planner agent for task decomposition. Returns: a feature branch named per conventions.branchPatterns checked out from the default branch, one TaskCreate task per acceptance criterion with dependencies set, and an initialized decision journal at {JOURNAL_DIR}/issue-{N}.md. Permitted skips: none — an issue without acceptance criteria is not decomposed; it goes back to the user (or Skill(issue-crafting)) first.
Pre-Conditions
Before creating a branch, confirm: the issue exists and is OPEN; it has acceptance criteria (otherwise ask the user or create them); no existing branch already addresses it; you have read the full body AND comments.
Branch Creation
DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name' 2>/dev/null || echo "main")
git fetch origin "$DEFAULT_BRANCH"
git checkout -b "feature/issue-{N}-{desc}" "origin/$DEFAULT_BRANCH"
Patterns from settings.json → conventions.branchPatterns: feature/issue-{N}-{desc}, fix/issue-{N}-{desc}, docs/issue-{N}-{desc}. {desc} is 3-5 kebab-case words.
Issue Context Loading
Fetch in parallel: gh issue view $N --json title,body,labels,assignees,milestone and gh issue view $N --comments. Extract: title; acceptance criteria (each - [ ] item becomes a task); labels (inform approach); related issues.
Impact Analysis
Grep for issue keywords and check git log --oneline -10 -- <related path>. Map acceptance criteria to likely file changes. Flag when the issue touches multiple modules (coordination), shared utilities (side-effect risk), or test fixtures (cross-suite updates).
Task Decomposition
For each acceptance criterion:
TaskCreate(
subject: "Implement: {criterion summary}",
description: "Acceptance criterion: {full text}\nLikely files: {paths}\nVerification: {how to check}"
)
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.
- yesterday Changed · -56 lines af897d2de560
- 8d ago First seen · 125 lines · 60 tokens per session scan A a45d19e664c8
branch-and-task-management is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 805 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
create-pr
Creates a GitHub Pull Request on the current branch with a description focused on WHAT changed (not HOW). Uses emojis in the title and description. Use when the user asks to create a PR, open a pull request, or submit changes for review. Triggers on mentions of PR, pull request, merge request, or code review.
step4-archive-spec
Archive a completed spec — moves it to specs-archived and blocks agent access.
plan-roadmap
Create or update a prioritized product roadmap with phased milestones.
github-tracking
Composable GitHub issue/milestone tracking operations. Called by other skills — not invoked directly by the user.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…