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 melodic-software/claude-code-plugins --skill updategit clone --depth 1 https://github.com/melodic-software/claude-code-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/melodic-software/claude-code-plugins/update)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/update"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/update/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/update"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/update.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 | $0.00080 | $0.01591 |
| Opus 5.5 | $0.00032 | $0.00636 |
| Sonnet 5.5 | $0.00016 | $0.00318 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Last upstream sync: !grep -m1 '^- Last sync:' "${CLAUDE_SKILL_DIR}/upstream.md" >/dev/null 2>&1 && grep -m1 -o 'Last sync:.*' "${CLAUDE_SKILL_DIR}/upstream.md" 2>/dev/null || echo "never — run this skill with --check"
Purpose
Keep the /firecrawl:firecrawl wrapper skill in sync with its two upstream dependencies: the
firecrawl-cli npm package (ships new versions roughly weekly) and the upstream canonical skill at
https://www.firecrawl.dev/agent-onboarding/SKILL.md (evolves alongside it). The wrapper skill
owns its content. Upstream is a source, not a parallel install.
Maintainer-facing: run this in a working-tree checkout of this plugin (the marketplace clone, or a
directory loaded via --plugin-dir), never against an installed marketplace copy, the apply path
rewrites upstream.md inside this skill directory, and consumers receive updates through
/plugin marketplace update. Drift detection uses the sidecar upstream.md (SHA tracking): upstream
SKILL.md is fetched fresh on --check and hashed; the sidecar records the prior hash for diff. No
vendored snapshot is kept. The action is advisory, the two approval gates in Safety below keep every
mutation behind an explicit yes.
Invocation
| Invocation | Effect |
|---|---|
/firecrawl:update --check |
Read-only drift report. Fetches upstream + npm metadata, compares against upstream.md. No mutations. |
/firecrawl:update |
Full update pipeline with two approval gates |
When to invoke, the modes, and the full update pipeline: read context/update-flow.md. The
preservation invariants and safety guarantees below stay inline.
Preservation rules (for any skill-content integration)
These are the invariants an integration run must keep in the /firecrawl:firecrawl wrapper skill,
in this exact form:
- Single-line YAML
descriptionwithUse when:and skip guidance phrase lists - Frontmatter fields:
description,argument-hint,user-invocable: true,disable-model-invocation: false(noname; the skill takes its name from the directory, per thenamerow of Frontmatter reference, as of 2026-10-11; recheck when that row's default changes) - Pre-computed context block at top, using
firecrawl --statusfor the health line - "Core pattern. Write to disk, Read selectively" rule: every non-trivial example writes to a
mktemp-created spill file with-o,Reads selectively, and the spill file is removed after the Read (kept only when the user asked for the file itself) - "When NOT to use this skill" section with the doc-site-reader-first and synthesis-tool escalation ordering
- The pointer to this maintainer update skill (
/firecrawl:update), the wrapper skill delegates its update/drift concern here rather than carrying it inline - Gotchas section with the "don't run
firecrawl init, don't runfirecrawl login" prohibitions - Imperative tone, no marketing language
What ships with it
5 files 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.
- 7d ago Changed 6f4c87af78b9
- 9d ago Changed 234cee42f6be
- 17d ago Changed e31707d50cf1
- 22d ago Changed · +1 lines bf3c734a9153
- 1mo ago Changed 42383c88b7a7
- 1mo ago First seen · 102 lines · 80 tokens per session scan A ca3bfc4fa4c3
update is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,591 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 2026-09-03.
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).
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.
return-none-for-failure
For graceful failure: return None or False instead of exceptions, let caller decide how to handle failure.