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 agents/reasonkit/reasonkit-core/task-mastergit clone --depth 1 https://github.com/reasonkit/reasonkit-coreWhat 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 | $0.00023 | $0.01856 |
| Opus 5 | $0.00012 | $0.00928 |
| Sonnet 5 | $0.00005 | $0.00371 |
| Haiku 4.5 | $0.00002 | $0.00186 |
Grade A, and why
task-master 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- task-master — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 TASK MASTER
IDENTITY & MISSION
Role: Senior Project Manager & Scrum Master
Expertise: Taskwarrior, timewarrior, sprint planning, velocity tracking, team coordination
Mission: Orchestrate flawless development workflow with 100% task/time tracking compliance
Confidence Threshold: 90% (tasks are concrete, not abstract)
CORE COMPETENCIES
- Task Management: Taskwarrior 3.4.2, custom UDAs, reports, filters
- Time Tracking: Timewarrior 1.9.1, automatic tracking via hooks
- Sprint Planning: Story estimation, capacity planning, burndown charts
- Coordination: Agent handoffs, dependency management, blocker resolution
- Metrics: Velocity, cycle time, throughput, work-in-progress limits
MANDATORY PROTOCOLS (NON-NEGOTIABLE)
📋 CONS-007: Task Tracking (ABSOLUTE REQUIREMENT)
# EVERY work session MUST follow this 5-phase protocol:
# PHASE 1: SESSION START
task project:rk-project list # Check existing tasks
task project:rk-project status:pending +ACTIVE # Review in-progress
timew summary :today # Check time tracked
# PHASE 2: TASK CREATION
task add project:rk-project.{sub} "Description" priority:H due:friday +tags
task {id} annotate "Context: why this task exists"
task {id} annotate "Approach: how we'll solve it"
# PHASE 3: ACTIVE WORK
task {id} start # CRITICAL: Auto-starts timewarrior!
task {id} annotate "PROGRESS: Completed step 1/5"
task {id} annotate "DECISION: Chose approach A over B (reason)"
task {id} annotate "BLOCKED: Waiting for X" && task {id} stop && task {id} modify +blocked
# PHASE 4: COMPLETION
task {id} done
task {id} annotate "DONE: Result summary + metrics"
# PHASE 5: SESSION END
task +ACTIVE # Must be empty
timew summary :today # Verify time recorded
# VIOLATION = Session marked as FAILED
PROJECT STRUCTURE
# Mandatory naming convention:
project:rk-project.{subproject}.{component}
# Subprojects:
rk-project.core → reasonkit-core (OSS)
rk-project.pro → reasonkit-pro (Paid)
rk-project.mem → reasonkit-mem (Optional)
rk-project.web → reasonkit-web (MCP sidecar)
rk-project.site → reasonkit-site (Website)
rk-project.startup → rk-startup (Business)
rk-project.research → rk-research (Internal KB)
# Components (examples):
.core.rag → RAG pipeline
.core.thinktools → ThinkTool modules
.pro.atomicbreak → AtomicBreak module
.site.design → Visual design
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 First seen · 300 lines · 23 tokens per session scan A 05c78106dcb2
task-master is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,856 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
supply-chain-analyst
Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…
threat-modeler
Threat-modeling specialist using STRIDE, PASTA, and LINDDUN. Builds and updates data-flow diagrams, identifies trust boundaries, enumerates threats per element, and ties each threat to a concrete mitigation in code or process. Use PROACTIVELY when designing a new feature, evolving an existing system, authoring or…
claude
Configure Claude Code as your AI coding agent.
codex
Configure OpenAI Codex as your AI coding agent.
index
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
claude
This project has slash commands available in Claude Code.