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 skills/fall-out-bug/sdp/designnpx skills add fall-out-bug/sdp --skill designgit clone --depth 1 https://github.com/fall-out-bug/sdpWhat 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 | $0.00012 | $0.01269 |
| Opus 5 | $0.00006 | $0.00634 |
| Sonnet 5 | $0.00002 | $0.00254 |
| Haiku 4.5 | $0.00001 | $0.00127 |
Grade A, and why
design 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@design
Multi-agent design (Arch + Security + SRE) with progressive discovery blocks.
When to Use
After @idea, or directly from a feature description. Creates workstream files with AC and scope.
Pre-flight
Before creating draft: ls docs/drafts/idea-* — do not duplicate. If an idea draft already covers this topic, reuse or extend it instead of creating a new one.
Beads from review: In scope by default. Mark OOS only with explicit justification (e.g. "duplicate", "superseded by prior work").
Workflow
1. Load requirements
docs/intent/{task_id}.jsonordocs/drafts/idea-*.mdif available- Or: use the feature description directly
2. Progressive discovery — unless --quiet
3-5 discovery blocks, 2-3 questions each:
- Architecture: What components change? What's the data model?
- Security: Any auth, crypto, or boundary concerns?
- Operations: Any monitoring, logging, or CI concerns?
After each block: Continue / Skip / Done
3. Generate workstream files
When source is beads (review findings): For each bead, run bd show <id> and grep the codebase for the fix. If already fixed, run bd close <id> and remove from scope. Do not create WS for beads that are already addressed.
Create docs/workstreams/backlog/00-FFF-SS.md for each deliverable.
Required sections:
# 00-FFF-SS: Feature Name — Step Description
Feature: FFFF (sdp_dev-XXXX)
Phase: N
Status: Backlog
## Goal
One paragraph: what and why.
## Scope Files
List exact file paths or directory prefixes this workstream touches.
Used by sdp-guard for boundary checking and CI scope-compliance.
- internal/evidence/
- cmd/sdp-evidence/main.go
## Dependencies
- 00-FFF-01: prerequisite workstream (if any)
## Acceptance Criteria
Specific, testable, binary (pass/fail):
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] go build ./... passes
- [ ] go test ./internal/evidence/... passes
4. Create Beads issues
bd create --title="WS FFF-SS: Short title" --type=task
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 · 150 lines · 12 tokens per session scan A 7bc239b9ce72
design is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 1,269 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 skills, from other repositories
typescript-best-practices
Enforces TypeScript best practices and modern patterns.
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
Unit Test Improver
Reviews existing unit tests for gaps, weak assertions, and missing edge cases, then rewrites them to be more robust.
Refactor Planner
Creates a safe, step-by-step plan to refactor messy code without breaking existing behavior.
code-discipline
Coding methodology for production-grade software development. Enforces structured thinking before coding, verifying reality, simplicity, surgical changes, contract awareness, and verifiable success criteria. Use when writing, reviewing, or refactoring code that needs to remain reliable over time, including production…
umbra-trust-review
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.