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 commands/gregorbiswanger/featherspec/sdd-architecture-updategit clone --depth 1 https://github.com/GregorBiswanger/featherspecWrote 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/commands/gregorbiswanger/featherspec/sdd-architecture-update)<a href="https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-architecture-update"><img src="https://agentmods.dev/badge/commands/gregorbiswanger/featherspec/sdd-architecture-update.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 5.1 | $0.00014 | $0.01174 |
| Opus 5 | $0.00007 | $0.00587 |
| Sonnet 5 | $0.00003 | $0.00235 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
sdd-architecture-update 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-architecture-update — Architecture Reconciliation
The user may name a focus area (module, folder, or concern) after the command; it is optional.
Gather context first
Read the current architecture: snapshot from AGENTS.md. Inspect the tree's top two levels
for new structures, and verify every path the snapshot names (entrypoints, modules, shared) at
whatever depth it sits — boundary changes hide below level two.
Goal
Compare the actual repository structure with the architecture: snapshot in AGENTS.md and
reconcile them.
Steps
- Read the tree and the current snapshot.
- Identify changes that matter architecturally: new/moved/removed top-level folders; new
entrypoints, apps, services, packages, modules; changed boundaries or shared components.
Where
.memory-bank/systemPatterns.mdholdsfs-knowledge:blocks, read.claude/rules/knowledge-records.mdnow and treat those records as reconciliation targets too: a moved or renamed path that a record's evidence names is drift like any other. - Present a delta report: what changed (observed), why it matters (brief), and the proposed updates to the snapshot and Memory Bank docs.
When reconciliation is not enough
If the tree shows several structures the snapshot cannot place, the snapshot names paths that
no longer exist, or the focus area sits under unmapped: — do not guess. Recommend
/sdd-architecture-scan (with the focus path) in the delta report instead. (This escalation
rule is owned here; AGENTS.md only mandates running this workflow unprompted.)
Confirmation gate
Before writing anything, ask:
- "Is this the change you expected?"
- "Anything else I should include (e.g., context not visible in the code)?"
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.
- 6d ago First seen · 95 lines · 14 tokens per session scan A b24be580974f
sdd-architecture-update is a command published in the GitHub repository GregorBiswanger/featherspec (47 stars, last pushed 7d ago), licensed MIT. It adds 14 tokens to every session and 1,174 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 2026-08-30.
Other commands, from other repositories
sddp-implement-qc-loop
Command description: Run implement and QC in a continuous loop. Argument hint: [optional: feature directory or branch name] Command category: orchestration Prerequisites: spec, plan, tasks.
sddp-specify
Command description: Create a feature specification from a feature description. Argument hint: [feature description] Command category: feature-delivery Prerequisites: project-instructions.
sddp-clarify
Command description: Reduce ambiguity in the current feature specification. Argument hint: [optional: ambiguity focus or feature directory] Command category: feature-delivery Prerequisites: spec.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
sddp-tasks
Command description: Generate an actionable task list from the current plan. Argument hint: [optional: feature directory or task focus] Command category: feature-delivery Prerequisites: spec, plan.
sddp-amend
Command description: Propagate a bootstrap change across canonical project artifacts and the project plan. Argument hint: [project-level change to propagate across bootstrap artifacts] Command category: project-bootstrap Prerequisites: project-instructions, product-document, technical-context, project-plan.