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 juxt/claude-plugins --skill put-downgit clone --depth 1 https://github.com/juxt/claude-pluginsWrote 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/juxt/claude-plugins/put-down)<a href="https://agentmods.dev/skills/juxt/claude-plugins/put-down"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/put-down/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/juxt/claude-plugins/put-down"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/put-down.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 | $0.00077 | $0.00688 |
| Opus 5.5 | $0.00031 | $0.00275 |
| Sonnet 5.5 | $0.00015 | $0.00138 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
put-down 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Put-down
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
The code state survives a session on its own; the analysis state does not. What the session learned, the questions it left open and the work it discovered all evaporate when it ends, unless they are on the issue.
The success criteria for this skill is that the next session can resume from the issue and its links alone.
Before you start
-
Load
chalk:issue, which loadschalk:voiceand carries the description's palette, the correction rules, the weeding loop and the filing mechanics. -
Ground it in the repo, not the transcript.
git status,git logand the branch say what landed; the transcript only says what was attempted. -
Read the session's plan, where
chalk:pick-upstarted one. What the issue's next reader needs from it — open questions, and decisions that bear on the problem — reaches the issue throughchalk:issue's own path below.
1. Ensure the description is correct and up-to-date.
Through chalk:issue's own path: Correcting the description, Open questions, then Weed the draft.
Put-down adds no second shape for the description.
- Every open note goes in, IDs unchanged, whatever types the session holds. A note answered this session is deleted, its answer moved to wherever it now belongs.
2. Raise and link cards the session discovered as appropriate
Each piece of work the session found but didn't become a candidate for an issue, filed through chalk:issue, unless one already exists.
If it is in any way unclear, you MUST confirm with the user which ones they want raising.
-
Parent/child relationships MUST be wired in the tracker, as must blocked-by where the tracker models it. A child known only from a mention in the parent's text doesn't show up in the tracker's own view of the parent.
-
A card this work turned out to wait on gets the dependency written onto it, through
chalk:issue's own path, and not only the edge.
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.
- 4d ago Changed · +2 lines 86d29d090ae3
- 11d ago Changed · +3 lines e020aa2c4c9a
- 13d ago First seen · 54 lines · 77 tokens per session scan A b01d1143fa6b
put-down is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 688 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…