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 agentmods add skills/vscarpenter/gsd-task-manager/claude-code-primitivesnpx skills add vscarpenter/gsd-task-manager --skill claude-code-primitivesgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/vscarpenter/gsd-task-manager/claude-code-primitives)<a href="https://agentmods.dev/skills/vscarpenter/gsd-task-manager/claude-code-primitives"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/claude-code-primitives.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 | $0.00056 | $0.00331 |
| Opus 5 | $0.00028 | $0.00166 |
| Sonnet 5 | $0.00011 | $0.00066 |
| Haiku 4.5 | $0.00006 | $0.00033 |
Grade A, and why
claude-code-primitives scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Claude Code Primitives
- Routing: Commands initiate, subagents verify, hooks gate.
- Slash Commands (
.claude/commands/): Short, repeatable actions. Canonical text of prompts lives here (e.g.,/qspec,/tdd,/qcheck). - Skills (
.claude/skills/): Complex multi-step workflows. Write descriptions as triggers ("when should I fire?"). Provide goals, constraints, and a "Gotchas" section. - Subagents (
.claude/agents/): Spawn for fanning out or parallel reads. Skip for <3 tool calls. Read-only agents usehaiku; write agents usesonnet/opuswithisolation: worktree. - Agent teams vs subagents: Use subagents for scoped delegation inside one workstream. Use teams when work should split across longer-lived sessions that coordinate.
- Hooks: Enforce standards mechanically (e.g.,
PostToolUse,Stop). Hook types: shell commands, prompt hooks, MCP tool hooks. - Hooks receive event data as JSON on stdin. Read fields with
jq, for example.tool_input.file_path; do not rely on$CLAUDE_FILE_PATHstyle variables unless explicitly configured.
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.
- 3d ago First seen · 15 lines · 56 tokens per session scan A 5e20adb48f83
claude-code-primitives is a skill published in the GitHub repository vscarpenter/gsd-task-manager (24 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 331 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 2026-08-30.
Other skills, from other repositories
lastest
Run visual regression tests, review screenshot diffs, and manage baselines on a Lastest instance via the @lastest/mcp-server MCP tools.
lastest
Lastest is a visual regression testing platform. It records browser tests, runs them via Playwright, diffs screenshots, and uses AI to classify changes. Available as an MCP server for AI agent integration.
Lastest design system
Visual + content rules for Lastest, the free open-source visual regression testing platform. Anchored on the Delta Mark logo + 5-stop split-complementary palette.
xcodebuildmcp-packaging-resource-review
Use when reviewing XcodeBuildMCP packaging, resource-root, build artifact, bundled AXe, schema, manifest, and portable macOS distribution changes.
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
fix-reported-issue
Triage and fix the oldest unresolved issue from the production issuereports table. Use this skill whenever the user asks to check for reported issues, fix a reported bug, address user feedback, work on issue reports, or triage production issues. Also use when the user says things like "check prod for issues", "any new…