Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install animationWrote 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/melodic-software/claude-code-plugins/produce)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/produce"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/produce/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/melodic-software/claude-code-plugins/produce"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/produce.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 | $0.00100 | $0.01737 |
| Opus 5.5 | $0.00040 | $0.00695 |
| Sonnet 5.5 | $0.00020 | $0.00347 |
| Haiku 4.5 | $0.00010 | $0.00174 |
Grade A, and why
produce 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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce
Turn a brief and one or more style packs into a film. Nothing past the boards renders until the
user approves them. shots.json is the only list of shot cuts.
Requirements are the plugin README's. Run each script as
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/pydeps.py run --data-dir "${CLAUDE_PLUGIN_DATA}" -- <script> ...,
which uses the packages the SessionStart hook installed.
The gate script ${CLAUDE_PLUGIN_ROOT}/scripts/produce.py needs only the standard library.
Rendering is ${CLAUDE_PLUGIN_ROOT}/scripts/render.py; the pack check is
${CLAUDE_PLUGIN_ROOT}/scripts/inkstats.py.
Production directory
One directory the user names. produce.py init <dir> creates each missing skeleton file and never
overwrites one. Paths in these files are relative to the production directory and stay inside it.
| Path | Who writes it | What it holds |
|---|---|---|
brief.md |
you | Subject:, Length:, Audience:, Packs: (comma-separated pack names), Delivery: |
boards/style-guide.md |
you | Pack: equal to palette.json pack. Under Differs from the pack:, each bullet says measured or judgment |
boards/palette.json |
you | pack, ink and paper as #rrggbb, tones as {lv, color} objects, optional tolerance |
boards/vibe.md |
you | reference images, each with a credit. A film with none still says Credit: |
boards/models/<name>.md .js .png |
you | at least one character sheet. The .js is a scene module (step 2); the .png is its turnaround |
boards/elements/<name>.md .js .png |
you | the same shape, only for elements you need |
boards/storyboard.json |
you | panels: {shot, panel, t, png, action, camera, caption?}. png is a relative path to a real file |
boards/approval.json |
produce.py approve |
{approved, note, boards_digest}. Never hand-write it |
shots.json |
you, after approval | {fps, size:[w,h], shots:[{id, t0, t1, scene, pack, audio?:{path, start}}]}. The first t0 is 0, and each t1 is the next t0 |
frames/render.json |
render.py |
the delivered film. Its fps, size, and duration match the shot list |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · -6 lines · -22 tokens per session e4eeec7583e3
- 13d ago Changed · +1 lines 5558e56b3526
- 16d ago Changed · +11 lines 62da5a3291a5
- 17d ago First seen · 89 lines · 122 tokens per session scan A d95c9e62db3c
produce is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,737 once invoked, about $0.0004 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 2026-09-29.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.