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 zhitongblog/unflick --skill unflick-navigategit clone --depth 1 https://github.com/zhitongblog/unflickWrote 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/zhitongblog/unflick/unflick-navigate)<a href="https://agentmods.dev/skills/zhitongblog/unflick/unflick-navigate"><img src="https://agentmods.dev/badge/skills/zhitongblog/unflick/unflick-navigate/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/zhitongblog/unflick/unflick-navigate"><img src="https://agentmods.dev/badge/skills/zhitongblog/unflick/unflick-navigate.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 | $0.00098 | $0.00690 |
| Opus 5.5 | $0.00039 | $0.00276 |
| Sonnet 5.5 | $0.00020 | $0.00138 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
unflick-navigate 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 2mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unflick: find the moment, then go to it
Seeking by seconds is a poor way to find a scene. unflick can seek by what was said, by chapter, and by a name the user gave a spot earlier.
By what was said
The player reads the subtitle track it already has open — embedded, sidecar, or
one whisper.cpp generated (see the unflick-subtitles skill).
search_transcript(query, limit?)— every match with its timestamp.seek_to_text(query, occurrence?)— jump to a match. Lands just before the line so the user hears it from the start.transcript_get()— the whole transcript as timed cues.
unflick transcript search "the treasure"
unflick transcript seek "the treasure" --occurrence 2
If there is no readable subtitle track, these say so — generate one first rather than guessing at timestamps.
By chapter
chapter_list(),chapter_seek(index),chapter_next(),chapter_prev().generate_chapters(count?)— derive chapters from pauses in the transcript when the file has none of its own.set_chapters(chapters)— supply a list you wrote yourself:[{"time": 0, "title": "Cold open"}, …].
Generated and supplied chapters are real navigation, not a side note: they mark
the progress bar and answer chapter_seek. They are cleared when the file
changes, so set them for the file that is playing now.
By name
bookmark_add(name?, position?, file?)— defaults to where playback is.bookmark_list(file?, all?),bookmark_goto(id)— seeks within the current file, or opens the bookmarked file if it is a different one.bookmark_rename(id, name),bookmark_remove(id),bookmark_clear(…).
unflick bookmark add --name "the good bit"
unflick bookmark list
unflick bookmark goto 1
Bookmarks survive restarts. They are keyed by path — for a disc that means the drive letter, so a bookmark left on one DVD will be offered on the next disc in that drive.
Guidance
- Prefer
seek_to_textover arithmetic onget_status.position: the user asked for a line, not a number. - Repeated
bookmark_addwithin a second is treated as a correction of the same spot, not a second bookmark — say so rather than reporting two. bookmark_clearrefuses to guess "everything": pass a file, orall.
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.
- 2mo ago First seen · 71 lines · 98 tokens per session scan A 40113c15de8f
unflick-navigate is a skill published in the GitHub repository zhitongblog/unflick (1 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 690 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 2026-09-09.
unflick-navigate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unflick-navigatezhitongblog/unflick | Skill | 1 | 1mo ago | MIT | A | 98 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |