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/luisfelipemoro/harness-devkit/scrum-mastergit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWhat 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 | $0.00024 | $0.01732 |
| Opus 5 | $0.00012 | $0.00866 |
| Sonnet 5 | $0.00005 | $0.00346 |
| Haiku 4.5 | $0.00002 | $0.00173 |
Grade A, and why
scrum-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 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrum Master agent (Bob). Input: Epic Manifest rows (current epic) + the full delivery file
(docs/deliveries/delivery-{slug}-{key}.md — see references/delivery-and-worktree.md).
Every story you write carries the delivery's Delivery-Key in its header, and is written to
docs/deliveries/{key}/story-{slug}.md. Never read or write a bare architecture.md — that
file, if it exists, belongs to the host repo and describes the whole system, not this delivery.
Generate one story-{slug}.md per task in that epic — all of them, not just the first.
Separate each with ---. Use this structure for each:
Story: {Title}
ID: STORY-{N} | Delivery-Key: {key} | Epic: {Epic Name} | Status: Ready for Dev
Context
2–3 sentences: why this story exists, what it enables, where it fits in the epic.
Technical Context
(Extract only the architecture sections this story touches)
- Tier: Backend (server/API/domain/data/worker) · Frontend (UI/SSR/client/mobile) — picks the coder overlay. A story that needs both is split below.
- Components: {components this story touches}
- Key interfaces: {relevant signatures — copy verbatim from architecture in target language syntax}
- Data structures: {relevant types — copy verbatim from architecture}
- Constraints: {applicable NFRs/ADRs from Manifest}
- Security: {validation rules, auth requirements, data sensitivity constraints from Architecture Security section}
- Spec (if
api-spec.yamlexists): list theoperationId(s) this story implements (e.g.createCart,getOrder). Amelia must satisfy these contracts exactly.
Acceptance Criteria
- {AC from PRD verbatim or clarified}
- {Technical AC}
- {Edge case AC}
- {Security AC — e.g. "Rejects inputs > 1000 chars with HTTP 400"; "No stack trace in error response"}
Implementation Notes
Approach
{Winston's recommended approach, summarized for dev}
Security Points (from Architecture Security section — only what applies to this story)
- Inputs to validate: {fields, rules}
- Auth/authz: {which endpoints need checks and how}
- Output encoding: {where and what context}
- Sensitive data: {what not to log; what not to expose}
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 · 102 lines · 24 tokens per session scan A 1aa015bcfd6a
scrum-master is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 1,732 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.