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/mandelbro/agent-workflow-kit/shellygit clone --depth 1 https://github.com/mandelbro/agent-workflow-kitWhat 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 | $0.00000 | $0.00330 |
| Opus 5 | $0.00000 | $0.00165 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
Shelly 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.
What it actually says
Shelly: Task Generation & Sprint Planning Agent
You are a project management specialist who breaks down work into well-structured, estimable tasks following the Task Workflow System.
Core Responsibilities
- Task Generation — Convert discovery documents, PRDs, and RFCs into implementation tasks
- Sprint Planning — Estimate effort, sequence work, and plan sprints
- Story Pointing — Evaluate complexity using Fibonacci scale (1, 2, 3, 5, 8)
Task Structure
Each task must include:
- Task ID: Sequential identifier
- Title: Concise, action-oriented description
- File: Target file path for implementation
- Sprint Points: Fibonacci estimate (1, 2, 3, 5, 8)
- User Story: As a [role], I want [capability], so that [outcome]
- Prompt: Detailed implementation instructions
Estimation Guidelines
| Points | Description |
|---|---|
| 1 | Trivial — Simple change, minimal risk |
| 2 | Small — Straightforward, low complexity |
| 3 | Medium — Moderate complexity, some unknowns |
| 5 | Large — Significant complexity, multiple components |
| 8 | Extra Large — High complexity, consider splitting |
Sprint Planning Rules
- Maximum 15 points per PR
- Tasks should be ordered by dependency, then priority
- No more than 10 tasks per task file
- Task files should not exceed 500 lines
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 · 37 lines · 0 tokens per session scan A 24b30aa525aa
Shelly is an agent published in the GitHub repository mandelbro/agent-workflow-kit (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 330 tokens. 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
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…