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 nortonx/ai-tooling-free --skill generate-specgit clone --depth 1 https://github.com/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/generate-spec)<a href="https://agentmods.dev/skills/nortonx/ai-tooling-free/generate-spec"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/generate-spec/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/nortonx/ai-tooling-free/generate-spec"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/generate-spec.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 | $0.00027 | $0.02379 |
| Opus 5 | $0.00014 | $0.01189 |
| Sonnet 5 | $0.00005 | $0.00476 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
generate-spec 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
<feature name>
- Required. The feature name in plain language; drives the slug, title, and reference-spec heuristic.
- Examples:
/generate-spec User Bulk Import,/generate-spec rate-limited webhook delivery
Copilot CLI note:
$ARGUMENTSdoesn't substitute in skills — include the argument inline in your prompt.
Generate Spec: $ARGUMENTS
Interview the user, draft a spec that follows the canonical template below (and mirrors any existing specs in this repo), and write it to disk only after the user approves. Specs are saved in ./specs/ (relative to the current working directory).
The user can stop the interview at any time. Respect that: partial specs are acceptable — omit empty sections rather than padding them with "TBD".
Step 1 — Orient
Before asking anything, discover the local spec conventions:
-
Check for an existing
./specs/directory. If it doesn't exist, tell the user you'll create it at write-time and ask whether they want a specific subdirectory (e.g.,frontend/,backend/,api/) or a flat layout. -
List existing specs by globbing
./specs/**/*.md. If any exist:- Note the subdirectory structure (flat vs. scoped like
frontend//backend/). - Pick one existing spec closest in shape to
$ARGUMENTSand read it as your reference. Use keyword heuristics on$ARGUMENTS:- "page", "component", "dialog", "form", "view", "UI", "composable", "hook" → prefer a frontend/UI-style spec.
- "endpoint", "API", "service", "handler", "guard", "middleware", "controller", "DTO" → prefer a backend/server-style spec.
- "database", "migration", "CI", "build", "release", "infra", "logging", "validation" → prefer an infra-style spec.
- Heuristic-override path: if the user's prompt also contains
as <scope>or--scope=<scope>(e.g.,/generate-spec User Bulk Import as backend), use that scope and skip the keyword heuristic. - Ambiguous match: if two or more buckets match the keywords (e.g., "API page component"), list the candidates and ask the user which to use rather than guessing.
- If no clear match, read the first 2-3 existing specs to establish the tone.
- Note the subdirectory structure (flat vs. scoped like
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 · 136 lines · 27 tokens per session scan A a1edbdb3f3a2
generate-spec is a skill published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 25d ago), licensed MIT. It adds 27 tokens to every session and 2,379 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
docs-sync
Keep project documentation in sync with code changes. Identifies which docs need updating after a PR merges or code changes, drafts the updates, and manages doc site structure (mkdocs, docusaurus, vitepress). Use when: (1) a PR just merged and docs may need updating, (2) the user says "update the docs" or "sync docs"…
project-planner
Triage ideas, problems, and feature requests into the right format: proposal doc, feature issue, or bug report. Repo-aware — discovers templates and docs structure from the current repository. Use when: (1) the user describes an idea, feature, or problem they want to track, (2) the user says "file a bug", "I have an…
intuitive-preflight
Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
api-integration-test
Create, maintain, and run gated Go integration tests for internal APIs and service-to-service clients (HTTP/gRPC). Use for endpoint verification, contract checks with real runtime config, opt-in execution, timeout/retry safety, and integration failure triage in Go services.
go-benchmark
Go performance benchmarking and pprof profiling specialist. ALWAYS use when writing benchmark functions (testing.B), generating or reading pprof profiles, interpreting flame graphs, finding memory allocation hotspots, comparing implementations with benchstat, or measuring ns/op / B/op / allocs/op. In Go code contexts…