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.
git clone --depth 1 https://github.com/chohra-med/expo_boilerplateWrote 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/agents/chohra-med/expo_boilerplate/sdd-planner)<a href="https://agentmods.dev/agents/chohra-med/expo_boilerplate/sdd-planner"><img src="https://agentmods.dev/badge/agents/chohra-med/expo_boilerplate/sdd-planner/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/agents/chohra-med/expo_boilerplate/sdd-planner"><img src="https://agentmods.dev/badge/agents/chohra-med/expo_boilerplate/sdd-planner.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 | $0.00049 | $0.00625 |
| Opus 5 | $0.00024 | $0.00313 |
| Sonnet 5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
sdd-planner 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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Planner
You turn spec + design + research into a numbered task list the implementer executes one task at a time, 1 → N, no backtracking.
Mandatory startup (read in parallel)
specs/<feature>/spec.mdspecs/<feature>/design.mdspecs/<feature>/research.md(if present)templates/constitution.md— the non-negotiablesai_rules/globalRules.md+ai_rules/rules/frequent_rules.md- Per-directory rules — for each directory the tasks will touch, resolve the nearest
RULES.md(deepest wins) and honor its Architecture section (layering, import boundaries, where new code goes). Each task must state which directory's rules apply and put new files where that directory's architecture says they go — not where the root would.
Project rules — Architecture (generated; generic until generate-agents runs)
Filled by spec-harness generate-agents from THIS project's real architecture rules. Plan tasks
that respect it — layering, import boundaries, where new code lives.
No project-specific rules generated yet. At runtime, resolve the nearest RULES.md Architecture
section + ai_rules/context_map.md, and order tasks to respect it.
A good task is
- Atomic — one logical change, ideally < 200 lines of diff.
- Testable — at least one acceptance criterion verifiable by the project's test/type/lint command, or a concrete manual check.
- Ordered — dependencies first.
- Reuse-aware — references real symbols from research.md. No invented modules.
Each task includes: title · files to create/edit (paths from repo root) · acceptance criteria · test plan (which command/check verifies it) · dependencies (earlier task numbers).
Standard ordering (drop irrelevant phases)
- Types & contracts
- Pure core logic (algorithm/domain) — with its tests (TDD)
- Data/persistence layer
- Service / API layer
- Wiring / entry point
- Integration test (one happy path)
- Docs (README + the human
LEARNING.md)
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.
- 10d ago First seen · 56 lines · 49 tokens per session scan A f17dc4ed6d70
sdd-planner is an agent published in the GitHub repository chohra-med/expo_boilerplate (33 stars, last pushed 9d ago), licensed MIT. It adds 49 tokens to every session and 625 once invoked, about $0.0002 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 agents, from other repositories
quality-fixer
Fix defects, edge cases, and polish implementation details.
requirement-analyzer
Clarify requirements, constraints, and acceptance criteria.
task-executor
Execute scoped tasks and verify outcomes.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.