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/alfredoperez/sdd/tasksnpx skills add alfredoperez/sdd --skill tasksgit clone --depth 1 https://github.com/alfredoperez/sddWrote 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/alfredoperez/sdd/tasks)<a href="https://agentmods.dev/skills/alfredoperez/sdd/tasks"><img src="https://agentmods.dev/badge/skills/alfredoperez/sdd/tasks.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 | $0.00020 | $0.01088 |
| Opus 5 | $0.00010 | $0.00544 |
| Sonnet 5 | $0.00004 | $0.00218 |
| Haiku 4.5 | $0.00002 | $0.00109 |
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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared Instructions
- Transition Logging — append a transition entry on every
.spec-context.jsonwrite
Steps
1. Load Context
If $ARGUMENTS is provided, use specs/{$ARGUMENTS}/ as the target directory.
Otherwise, find the most recently modified directory under specs/ that contains both spec.md and plan.md.
Read in parallel:
specs/{NNN}-{slug}/spec.md— feature name, requirements, scenariosspecs/{NNN}-{slug}/plan.md— approach, files to create/modifyspecs/{NNN}-{slug}/.spec-context.json— current step/task (if exists)
If no spec/plan found, stop: "Run /sdd:specify and /sdd:plan first."
Update specs/{NNN}-{slug}/.spec-context.json and append a transition entry per transition-logging:
{ "currentStep": "tasks", "currentTask": null, "progress": "loading", "next": "implement", "updated": "{TODAY}" }
2. Write specs/{NNN}-{slug}/tasks.md
Update specs/{NNN}-{slug}/.spec-context.json — set progress to "writing-tasks" and append a transition entry per transition-logging.
Read lib/templates/tasks.md, fill placeholders ({Feature Name}, {TODAY}), generate tasks based on the plan's file list, and write to specs/{NNN}-{slug}/tasks.md.
Phase rules:
- Phase 1: all core implementation tasks ordered by dependency (T001, T002, ...).
- Mark a task
[P]when it (a) touches files that no other task in its parallel group touches AND (b) has no data dependency on its siblings in the group. Two tasks that modify the same file are never both[P]. - Consecutive
[P]tasks form a parallel group that/sdd:implementruns as a batch of concurrent subagents. A task without[P]acts as a gate — it waits for everything above it. - After listing tasks, do a parallelism pass: group tasks by file path. Any task whose file appears nowhere else in Phase 1 (and has no data dep on siblings) is a
[P]candidate. A 5+ task spec with zero[P]markers should be reviewed before completing — that almost always means a missed pass. - When two interpretations are both legal, prefer the one with more
[P]markers. Sequential is the safe-but-slow fallback, not the default.
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.
- 5d ago First seen · 98 lines · 20 tokens per session scan A 8ae261d54070
sdd:tasks is a skill published in the GitHub repository alfredoperez/sdd (2 stars, last pushed 14d ago), licensed MIT. It adds 20 tokens to every session and 1,088 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…