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 knowledgeWrote 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/video-digest)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/video-digest"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/video-digest/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/video-digest"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/video-digest.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 | $0.00083 | $0.06137 |
| Opus 5.5 | $0.00033 | $0.02455 |
| Sonnet 5.5 | $0.00017 | $0.01227 |
| Haiku 4.5 | $0.00008 | $0.00614 |
Grade A, and why
video-digest scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(Windows), `brew install yt-dlp` (macOS), `pip install -U "yt-dlp[default,curl-cffi]"` or How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments. <watch [<url>|<n>]|<url>|queue <url>...|queue list|transcript <url>|resume <slug>>. Full form: watch [--target ] | watch [--target ] | watch [--target ] | | queue | queue list | transcript | resume
Pre-computed context
node "${CLAUDE_PLUGIN_ROOT}/skills/video-digest/extraction/preflight.mjs" --data-dir "${CLAUDE_PLUGIN_DATA}" --asr-python "${user_config.asr_python}"
If the report above did not run or shows no readiness lines, run that command by hand before any action.
Configured options
Claude Code substitutes these values when the skill loads. The spokes you open with Read arrive
unsubstituted, so they refer to this table. A cell that reads as a literal user_config token
rather than a value is unset: treat it as the default.
| Option | Value | Default |
|---|---|---|
library_dir |
${user_config.library_dir} |
. |
yt_dlp_js_runtimes |
${user_config.yt_dlp_js_runtimes} |
node |
yt_dlp_cookies_file |
${user_config.yt_dlp_cookies_file} |
empty |
yt_dlp_cookies_from_browser |
${user_config.yt_dlp_cookies_from_browser} |
empty |
max_concurrent_acquires |
${user_config.max_concurrent_acquires} |
1 |
asr_python |
${user_config.asr_python} |
empty |
How each value becomes a run.mjs flag: context/output-contract.md (library_dir) and
reference/sources/youtube.md (the yt-dlp options). asr_python applies to every source: when it
holds a non-empty value that is not a literal user_config token, pass --asr-python "<value>" as
a leading flag on every run.mjs invocation; otherwise omit it.
Video digest. YouTube and X
Absorb a single public video (transcript + visual frames), harvest reference links, fact-check
claims through deeper external research, and produce a prioritized repo-applicability menu.
Supported sources: YouTube (youtube.com, youtu.be) and X/Twitter status posts (x.com,
twitter.com). Fail closed on any other host, naming the supported sources; never guess.
What ships with it
60 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.
- context/companion-primary-sources.md 5.9 KB
- context/gotchas.md 5.4 KB
- context/output-contract.md 15 KB
- context/quality-gates.md 13 KB
- context/synthesis-contract.md 2.8 KB
- context/watch-pipeline.md 23 KB
- context/watch-queue.md 9.4 KB
- context/workflow.md 2.4 KB
- evals/evals.json 8.6 KB
- evals/fixtures/driver-video-goldens.json 2.5 KB
- evals/fixtures/x-status-goldens.json 3.9 KB
- extraction/.npmrc 19 B
- extraction/acquisition/acquire-partial-captions.test.js 5.8 KB runs code
- extraction/acquisition/acquire-retry-policy.js 1.4 KB runs code
- extraction/acquisition/acquire-retry-policy.test.js 1.5 KB runs code
- extraction/acquisition/acquire-staged.test.js 3.9 KB runs code
- extraction/acquisition/acquire-throttle.js 7.1 KB runs code
- extraction/acquisition/acquire-throttle.test.js 6.7 KB runs code
- extraction/acquisition/acquire-with-retry.js 1.8 KB runs code
- extraction/acquisition/acquire-yt-dlp-auth.js 2.9 KB runs code
- extraction/acquisition/acquire-yt-dlp-auth.test.js 3.4 KB runs code
- extraction/acquisition/acquire.js 15 KB runs code
- extraction/acquisition/acquire.test.js 8.1 KB runs code
- extraction/acquisition/adapter-argv-conformance.test.js 4.2 KB runs code
- extraction/acquisition/build-yt-dlp-args.js 8.5 KB runs code
- extraction/acquisition/build-yt-dlp-args.test.js 7.1 KB runs code
- extraction/acquisition/preflight-metadata.js 13 KB runs code
- extraction/acquisition/preflight-metadata.test.js 7.1 KB runs code
- extraction/acquisition/preflight-null-claim.test.js 1.8 KB runs code
- extraction/acquisition/select-caption.js 7.5 KB runs code
- extraction/acquisition/select-caption.test.js 7.5 KB runs code
- extraction/acquisition/spawn-yt-dlp-with-auth-fallback.js 3.3 KB runs code
- extraction/acquisition/spawn-yt-dlp-with-auth-fallback.test.js 4.8 KB runs code
- extraction/acquisition/video-metadata.js 3.3 KB runs code
- extraction/acquisition/video-metadata.test.js 2.0 KB runs code
- extraction/adapters/adapter-contract.js 22 KB runs code
- extraction/adapters/adapter-contract.test.js 10 KB runs code
- extraction/adapters/dispatch-cli.test.js 1.7 KB runs code
- extraction/adapters/fixture-adapter.test.js 5.6 KB runs code
- extraction/adapters/registry-conformance.test.js 2.7 KB runs code
- extraction/adapters/registry.js 4.5 KB runs code
- extraction/adapters/registry.test.js 3.5 KB runs code
- extraction/adapters/shared-adapter-suite.js 6.9 KB runs code
- extraction/adapters/x.js 39 KB runs code
- extraction/adapters/x.test.js 38 KB runs code
- extraction/adapters/youtube.js 6.4 KB runs code
- extraction/adapters/youtube.test.js 4.2 KB runs code
- extraction/evals/check-research-complete.js 3.0 KB runs code
- extraction/evals/check-research-complete.test.js 1.6 KB runs code
- extraction/evals/check-transcript-goldens.js 3.5 KB runs code
- extraction/evals/check-transcript-goldens.test.js 1.0 KB runs code
- extraction/evals/check-transcript-readability.js 3.2 KB runs code
- extraction/evals/check-watch-outcomes-layout.test.js 3.2 KB runs code
- extraction/evals/check-watch-outcomes.js 28 KB runs code
- extraction/evals/check-watch-outcomes.test.js 12 KB runs code
- extraction/evals/check-x-status-goldens.test.js 5.2 KB runs code
- extraction/evals/fixtures/clean-manual-course-snippet.vtt 205 B
- extraction/evals/fixtures/driver-manual-en-snippet.vtt 669 B
- extraction/evals/manual-caption-driver.test.js 2.2 KB runs code
- extraction/harvesting/analyze-harvested-repos.js 9.2 KB runs code
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 · +27 lines e99c86e4b9b3
- 3d ago Changed · +3 lines 4e5cbb52f69f
- 4d ago Changed · +24 lines 8bcab2475856
- 7d ago Changed · -1 lines · -22 tokens per session 968146dd9920
- 8d ago Changed · +4 lines 9eab2d31eacc
- 10d ago Changed · +21 lines bd6e81256a67
- 14d ago Changed 4c41cb16af94
- 15d ago Changed · +37 lines 267fb80d3bda
- 17d ago Changed · +1 lines 14f73acb8778
- 18d ago First seen · 254 lines · 105 tokens per session scan A bc9768f28e36
video-digest is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 6,137 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
count-combinations
For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
career-path-planner
Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.
learning-gap-analyzer
Map understanding, identify knowledge gaps, and build targeted learning plans with spaced repetition. Use when assessing knowledge levels, designing study plans, or optimizing learning paths.
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…
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).