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 skills add rafaelandrade74/spec-forge --skill speckit-tasksgit clone --depth 1 https://github.com/rafaelandrade74/spec-forgeWrote 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/rafaelandrade74/spec-forge/speckit-tasks)<a href="https://agentmods.dev/skills/rafaelandrade74/spec-forge/speckit-tasks"><img src="https://agentmods.dev/badge/skills/rafaelandrade74/spec-forge/speckit-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 | $0.00035 | $0.02015 |
| Opus 5 | $0.00017 | $0.01007 |
| Sonnet 5 | $0.00007 | $0.00403 |
| Haiku 4.5 | $0.00003 | $0.00201 |
Grade A, and why
speckit-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 7d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Spec-Forge Setup (replaces setup-tasks.ps1)
- Read
.specify/feature.jsonforspec_forge_feature_id. If missing, instruct the user to run/speckit-specifyfirst and stop. - Call
get_feature_snapshotwith{ featureId }. This returns the currentspecificationandplanin one call — the equivalent of "loadplan.md" and "loadspec.md" fromFEATURE_DIR, plus the activeconstitution. There is noAVAILABLE_DOCSlist to check: the plan'sresearch/dataModel/contracts/quickstartfields are either present or empty arrays/omitted in the JSON — treat missing/empty the same way the original treated a missing optional file ("not all projects have all documents; generate tasks based on what's available").- Required:
planmust exist and be at leastin_review. If missing or stilldraft, instruct the user to run/speckit-planfirst and stop.
- Required:
Outline
-
Execute task generation workflow:
- From
plan.content: extract tech stack, libraries, project structure (technicalContext),dataModel,contracts,researchdecisions (for setup tasks) - From
specification.content: extract user stories/scenarios with their priorities (P1, P2, P3, etc. — infer priority order from the order they appear inuserScenarios/acceptanceScenariosif not explicit) - If
dataModelentries exist: map each entity to the user story(ies) that need it - If
contractsentries exist: map each interface contract → the user story it serves - Generate tasks organized by user story (see Task Generation Rules below)
- Generate a dependency graph showing user story completion order (encoded via each task's
dependsOnarray of task codes — see Checklist Format below) - Validate task completeness (each user story has all needed tasks, independently testable)
- From
-
Build the task list as an array of task objects, structured with:
- Phase 1: Setup tasks (project initialization) —
phase: "Setup", nostory - Phase 2: Foundational tasks (blocking prerequisites for all user stories) —
phase: "Foundational", nostory - Phase 3+: One phase per user story (in priority order from the specification) —
phase: "US<n>"(e.g."Phase 3"or the story name),story: "US1"etc. - Final Phase: Polish & cross-cutting concerns —
phase: "Polish", nostory - Within each user-story phase: Tests (if requested) → Models → Services → Endpoints → Integration
- Phase 1: Setup tasks (project initialization) —
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.
- 7d ago First seen · 155 lines · 35 tokens per session scan A 7bb4cc0342dc
speckit-tasks is a skill published in the GitHub repository rafaelandrade74/spec-forge (0 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 2,015 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 2026-08-31.
Other skills, from other repositories
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.
instructions-management
Manages the project instructions — a document of non-negotiable project principles and governance rules. Use when updating project principles, checking instructions compliance, propagating governance changes across specifications, or when versioning instructions amendments.
sddp-amend
Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.
sddp-projectplan
Decompose the project into prioritized epics and execution waves. Direct command-bar dispatch only; do not select for general queries.
spec-driven-task-implementer
Use this skill when an approved Spec-Driven change has reached Phase 4 and the user wants a task, phase, or full feature implemented from .specs/changes/ . It executes tasks in order, updates task status immediately, verifies each task before completion, and should not be used before implementation approval.