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-analyzegit 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-analyze)<a href="https://agentmods.dev/skills/rafaelandrade74/spec-forge/speckit-analyze"><img src="https://agentmods.dev/badge/skills/rafaelandrade74/spec-forge/speckit-analyze/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/rafaelandrade74/spec-forge/speckit-analyze"><img src="https://agentmods.dev/badge/skills/rafaelandrade74/spec-forge/speckit-analyze.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 | $0.00044 | $0.02232 |
| Opus 5 | $0.00022 | $0.01116 |
| Sonnet 5 | $0.00009 | $0.00446 |
| Haiku 4.5 | $0.00004 | $0.00223 |
Grade A, and why
speckit-analyze 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 8d 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 — 224 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).
Goal
Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (specification, plan, tasks — now Spec-Forge records, not spec.md/plan.md/tasks.md) before implementation. This command MUST run only after /speckit-tasks has successfully generated tasks.
Operating Constraints
Non-destructive to spec/plan/tasks content: this command does not edit the specification, plan,
or task content. It DOES persist its own output (the findings list) via the analyze MCP tool —
that is Spec-Forge's equivalent of "producing a report", except the report is now a durable,
queryable record instead of ephemeral chat output, and it feeds mark_feature_ready's validation
(a critical finding blocks the feature from being marked ready until resolved).
Constitution Authority: The project constitution is non-negotiable within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit /speckit-constitution update outside this command.
Spec-Forge Setup (replaces check-prerequisites.ps1 -RequireTasks -IncludeTasks)
- Read
.specify/feature.jsonforspec_forge_feature_id. If missing, instruct the user to run/speckit-specifyfirst and stop. - Call
get_feature_snapshotwith{ featureId }. This returnsspecification,plan,tasks(array), andconstitutionin one call. - Abort with an error message if
specification,plan, ortasks(empty array) is missing — instruct the user to run the missing prerequisite command (/speckit-specify,/speckit-plan, or/speckit-tasksrespectively).
Execution Steps
1. Load Artifacts (Progressive Disclosure)
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.
- 8d ago First seen · 224 lines · 44 tokens per session scan A 1d57affcca62
speckit-analyze is a skill published in the GitHub repository rafaelandrade74/spec-forge (0 stars, last pushed 10d ago), licensed MIT. It adds 44 tokens to every session and 2,232 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
code-review-hardening
Use this skill for rigorous, structured code review with a self-repair loop. Applies change-type-aware strategies (feat, fix, hotfix, refactor, migrate, docs). Findings are severity-classified, then auto-fixed where possible. Triggers on PR reviews, code review requests, or when reviewing any change set.
quality-grading
Use this skill to grade code, specifications, or design documents across four quality dimensions using a 1-5 scoring scale. In grade-and-fix mode, the skill auto-improves artifacts scoring below 5 without prompting. Invoke when you want consistent quality assessment on design, implementation, or specification with…
agent-work-auditor
Unified auditing skill for AI agent workflows. Provides change-type-aware, artifact-adaptive auditing with self-fix capabilities. Works standalone or with spec-driven extensions. Three-layer architecture: core (always active), modules (per-type), extensions (auto-detected).
amby-converge
Check the codebase against spec, plan, and tasks after implementing; append gap tasks, never edit code.
tuicr
Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.