Borrowing it
Nothing to install: this file belongs to PedroMosquera/squadai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/skills/sdd/sdd-tasks/SKILL.mdgit clone --depth 1 https://github.com/PedroMosquera/squadaiWrote 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/skills/pedromosquera/squadai/sdd-tasks)<a href="https://agentmods.dev/skills/pedromosquera/squadai/sdd-tasks"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-tasks/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/skills/pedromosquera/squadai/sdd-tasks"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-tasks.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 | $0.00014 | $0.00634 |
| Opus 5 | $0.00007 | $0.00317 |
| Sonnet 5 | $0.00003 | $0.00127 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
sdd-tasks 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 9d 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.
What it actually says
SDD Tasks Skill
Break a design into a dependency-ordered list of implementation tasks. Each task must be independently completable and testable.
Steps
-
Identify leaf-level tasks: Find the smallest independently implementable units.
- Each task should produce a working, tested component
- Tasks should be completable in 30 min – 4 hours
- Tasks that cannot be tested independently need to be split further
-
Identify dependencies: Map which tasks depend on others.
- Task B depends on Task A if B requires A's output to compile or run
- Mark dependencies explicitly (not just "nice to have A first")
- Identify the critical path (longest chain of dependencies)
-
Build a dependency graph: Visualize the execution order.
Task 1 (no deps) Task 2 (no deps) Task 3 (depends: Task 1) Task 4 (depends: Task 1, Task 2) Task 5 (depends: Task 3, Task 4) -
Group into phases: Batch independent tasks for parallel execution.
- Phase 1: Tasks with no dependencies
- Phase 2: Tasks whose dependencies are complete after Phase 1
- Continue until all tasks are assigned
-
Estimate effort: Assign complexity to each task.
- S (Simple): ≤ 30 min — single function, no new abstraction
- M (Medium): 30 min–2 hrs — new type or interface, some design needed
- L (Large): 2–4 hrs — multiple components, requires careful integration
- Tasks estimated L or larger should be split if possible
-
Write acceptance criteria per task: Each task needs a clear done condition.
- What tests must pass?
- What behavior must be observable?
- What artifacts must exist (new file, new type, updated interface)?
Output Format
## Task Plan: <feature name>
### Dependency Graph
Phase 1 (parallel)
-
Task 1: [S] Depends on: none Done when:
-
Task 2: [M] Depends on: none Done when:
Phase 2 (parallel after Phase 1)
- Task 3: [M] Depends on: Task 1 Done when:
Summary
| Phase | Tasks | Effort |
|---|---|---|
| 1 | 2 | S+M |
| 2 | 1 | M |
| Total | 3 | ~3-4 hrs |
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.
- 9d ago First seen · 79 lines · 14 tokens per session scan A 5dda3cd76219
sdd-tasks is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 634 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 skills, from other repositories
harness-engineering
Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.
reap
Report how much of the context this agent loads is never used - unused skills, MCP servers, subagents, hooks and always-loaded prose - measured from real session transcripts. Use when asked why the context window is full, what is wasting tokens, or what is safe to remove.
gap
Measure the loaded-versus-fired gap - what fraction of each category of loaded context is ever actually invoked, and which MCP tools return mostly noise. Use when asked how much of the context is earning its place, or which categories are worst.
replay
Find, analyze, and share AI coding sessions with vibe-replay. Use when the user asks for a replay, wants to find a past session, run a session retro, share Cursor/Claude/Codex session context, or attach session context to a PR.
skill-doctor
Use the skill-doctor CLI or UI to inspect and manage AI-agent skills, rules, instructions, MCP resources, and context cost across supported platforms. Trigger when the user asks to scan or audit agent skills, find duplicates or trigger conflicts, investigate unsafe instructions, estimate context-token cost, compare…
skill-doctor-context-optimizer
Interactively keep the skills, MCP servers/tools, and plugins relevant to the user's current task, preview project-local disables for the rest, apply only explicitly confirmed controls through skill-doctor, and report approximate context-token savings. Trigger when the user asks to slim, optimize, prune, or reduce the…