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.
git clone --depth 1 https://github.com/qurore/speckit-tldrWrote 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/commands/qurore/speckit-tldr/speckit.tldr.generate)<a href="https://agentmods.dev/commands/qurore/speckit-tldr/speckit.tldr.generate"><img src="https://agentmods.dev/badge/commands/qurore/speckit-tldr/speckit.tldr.generate/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/commands/qurore/speckit-tldr/speckit.tldr.generate"><img src="https://agentmods.dev/badge/commands/qurore/speckit-tldr/speckit.tldr.generate.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 | $0.00065 | $0.03423 |
| Opus 5 | $0.00032 | $0.01711 |
| Sonnet 5 | $0.00013 | $0.00685 |
| Haiku 4.5 | $0.00006 | $0.00342 |
Grade A, and why
speckit.tldr.generate 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 12d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Kit TLDR — generate
Produce a fast, review-oriented overview of a feature's Spec Kit spec.md / plan.md.
The goal is to cut the time a PR reviewer spends getting oriented, while
deliberately surfacing the spots that deserve close reading rather than hiding
them. A TLDR here is an entry point into the document, not a substitute for it.
This command writes two local review artifacts and never modifies spec.md /
plan.md or any other source file. Remove the artifacts before opening the PR
with __SPECKIT_COMMAND_TLDR_CLEAN__.
User Input
$ARGUMENTS
The argument selects scope: spec, plan, both (default), or a path to a
specific .md file. Natural language in the user's message also counts ("just
the plan", "tldr the auth feature spec"). Consider it before proceeding.
Where this extension's files live
This extension is installed under .specify/extensions/tldr/ (see the
<!-- Config: ... --> comment at the top of this file). Its output templates are:
.specify/extensions/tldr/assets/tldr.template.html— the HTML dashboard template.specify/extensions/tldr/assets/tldr.template.md— the Markdown template
Read these from that location at render time (Step 4).
Core principles (read first)
- Regenerate from the canonical source. Always extract from the actual files in the repo / PR. Never trust a pre-existing summary an author may have written; a summary's omissions become the reviewer's blind spots.
- Surface risk, don't smooth it over. Ambiguities, missing acceptance criteria, and unanswered questions go to the top, not buried. The summary's job is to point at what to scrutinize.
- Point back into the document. Every extracted item records its source file and (when available) heading/line, so the reviewer can jump to the full text.
- Be diff-aware. Reviewers review the change, not the whole document. Mark what this PR added/changed and let the reviewer filter to just that.
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.
- 12d ago First seen · 266 lines · 65 tokens per session scan A c5f8037229e8
speckit.tldr.generate is a command published in the GitHub repository qurore/speckit-tldr (3 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 3,423 once invoked, about $0.0003 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 commands, from other repositories
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
launch-meta-campaign
Launch a complete Meta Ads campaign — campaign, ad set, and ad(s) — built paused and ready to review. Use when the user wants a new Facebook/Instagram campaign.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
create-topic
Research and generate a complete topic plan with keyword mapping, audience, angle, and competitive positioning.
duck-off
Turn off Rubber Duck mode and answer normally.