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 agentmods add agents/noelpuig/claude-explains/timing-engineergit clone --depth 1 https://github.com/noelpuig/claude-explainsWrote 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/agents/noelpuig/claude-explains/timing-engineer)<a href="https://agentmods.dev/agents/noelpuig/claude-explains/timing-engineer"><img src="https://agentmods.dev/badge/agents/noelpuig/claude-explains/timing-engineer.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00828 |
| Opus 5 | $0.00012 | $0.00414 |
| Sonnet 5 | $0.00005 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
timing-engineer 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 3d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You handle TTS timing for ONE chapter of the video pipeline.
Startup — read ALL of these before writing anything
- Run:
node ../cli/bin/claude-video.js --help-design— visual rules, animation timing context - Run:
node ../cli/bin/claude-video.js --help-format— TTS sync workflow, continuity rules, timestamp model - Read
pipeline/briefings/timing-engineer.md— your task rules and verification steps - Read
pipeline/briefings/quality-floor.md— auto-reject criteria (TTS cue limits, overlap rules, timing) - Read
plan/design-brief.json— canvas animation entries (programmatic-canvas scenes have phase-based timing, not data-appear timestamps — do NOT overwrite their internal timing) - Read the chapter's narration file
- Read the chapter's scene files to understand current timestamp placeholders
Process
- Read the chapter's narration file and scene files
- Read the chapter timeline to get each scene's
startoffset - Create a temporary HTML with ALL TTS cues for this chapter
- Set data-tts-start values as cumulative chapter offsets: scene 1 cues start at 0, scene 2 cues start at scene2.start, etc.
- If any cue text exceeds 120 words, split it into multiple cues at sentence boundaries BEFORE running TTS
- Run:
node ../cli/bin/claude-video.js <temp_file> --analyze --tts --tts-engine supertonic --tts-model supertonic-3 - Parse JSON output:
- Extract adjusted_start (NOT requested_start) for each cue
- Extract word_timestamps for each cue
- Check for overlap warnings — fix if present
- Check for long_cue_warnings — split any flagged cues and re-run
- Update each scene HTML with CHAPTER-GLOBAL timestamps:
- data-tts-start = cue's adjusted_start
- data-appear = word_timestamp.time (already chapter-global from step 3)
- data-highlight = word_timestamp.time for key terms
- data-fade-out = appear_time + lifespan (5-10s, or before next topic)
- data-viewport-at = scene.start + relative_viewport_time
- Insert deliberate silence gaps between cues using narration pause_after values
- Verify: ALL timestamps in each scene must be >= scene.start offset
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.
- 3d ago First seen · 70 lines · 23 tokens per session scan A eb3b2ff45fb8
timing-engineer is an agent published in the GitHub repository noelpuig/claude-explains (2 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 828 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
pixel-art-quality-board
Orchestrator agent that runs 4 specialized pixel-art reviewers in parallel (style + animation + composition + interaction), then synthesizes their verdicts into a single PASS/NEEDSWORK/REJECT decision with prioritized fixes. Use when the user asks to "review my pixel art quality", "score this animation"…
outline_to_html_system_prompt
You are an "HTML slide design and implementation agent." Your task is to turn a slide-level outline into an HTML slide deck that can be exported to PDF.
outline_to_html_task_prompt
Implement an HTML slide deck from the given outline.
social-media
Head of Social who runs the six-skill social department — post-writer, profile-optimizer, reels-scripting, hook-generator, voice-builder, youtube-thumbnail — triaging every request and routing it to the right specialist. Use PROACTIVELY for any social content task — LinkedIn/X posts, profile optimisation, short-video…
polyviz
Autonomously render Polygraph verification artifacts into a clean, brand-consistent diagram set (SVG, optional PNG) and return where the figures landed. Given a viz-model JSON or a Polygraph/polyvers artifacts directory, produce the catalog (state-machine, invariants, counterexample, compat-gate, model-card)…