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.clean)<a href="https://agentmods.dev/commands/qurore/speckit-tldr/speckit.tldr.clean"><img src="https://agentmods.dev/badge/commands/qurore/speckit-tldr/speckit.tldr.clean/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.clean"><img src="https://agentmods.dev/badge/commands/qurore/speckit-tldr/speckit.tldr.clean.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 | $0.00057 | $0.01317 |
| Opus 5 | $0.00028 | $0.00659 |
| Sonnet 5 | $0.00011 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade C, and why
speckit.tldr.clean scanned grade C with 1 finding 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf` a feature directory. How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Kit TLDR — clean
The companion to __SPECKIT_COMMAND_TLDR_GENERATE__. It cleans up the review
artifacts that the generate command writes (*.tldr.html / *.tldr.md, under
specs/<feature>/tldr/) so they do not get committed in a pull request. The
TLDRs are a local reviewing aid, not something the PR itself should carry.
User Input
$ARGUMENTS
The argument selects scope: spec, plan, both (default), all, or a path.
Natural language in the user's message also counts ("clean up the tldrs",
"remove the plan tldr"). Consider it before proceeding.
Core safety rules (read first)
- Only ever delete generated TLDR artifacts. In scope: files matching
*.tldr.htmland*.tldr.md, plus atldr/directory once it is empty. NEVER deletespec.md,plan.md,research.md,tasks.md,contracts/, or anything else — those are the source, not the output. - Discover → list → confirm → delete. Always show the exact list of paths you are about to remove and get the user's confirmation first, unless the user already gave an explicit go-ahead ("yes, delete them", "force", "no prompt").
- Never delete with a wildcard. Expand the glob to explicit paths first, show
those paths, then remove exactly those. Do not pass
*torm, and neverrm -rfa feature directory. - Respect git. A file that is already committed must be removed with
git rm(so the deletion is staged and actually leaves the PR); a file that is untracked is simply removed from disk.
Step 1 — Resolve scope
Parse the argument and also honor natural language:
spec→ onlyspec.tldr.html/spec.tldr.md.plan→ onlyplan.tldr.html/plan.tldr.md.bothor no argument → both the spec and plan TLDRs for the target feature.all→ every*.tldr.html/*.tldr.mdunderspecs/across the repo.- A path (a file, or a
specs/<feature>/dir) → operate on exactly that.
Find the target feature directory the same way the generate command does: if the
user names a feature, find the matching specs/*<feature>*/ directory; otherwise
infer from the current PR/branch (the changed specs/<feature>/ files); if still
ambiguous, list the candidates under specs/ and ask. For all, skip feature
resolution and search the whole repo.
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.
- 11d ago First seen · 125 lines · 57 tokens per session scan C 13634657071f
speckit.tldr.clean is a command published in the GitHub repository qurore/speckit-tldr (3 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 1,317 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
ship
Open a pull request for the current branch, drive it green, and merge it.
workspace-sync
(Workspace) Cross-repo "what changed while I was away" — discover, reconcile, and report.
discover-repos
(Workspace) Detect new repositories locally and on the GitHub org, propose clone + bootstrap.
sync-main
Reconcile git main vs. the ledger — what merged while you were away (read-only).
init-workspace
(Workspace) Set up the optional multi-repo orchestrator — Registry + Config.
pr
Open the PR for a verified story (In Review → In PR), body filled from the ledger.