Borrowing it
Nothing to install: this file belongs to okikeSolutions/guerillaglass. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/okikeSolutions/guerillaglass/main/.agents/skills/guerilla-editing/SKILL.mdgit clone --depth 1 https://github.com/okikeSolutions/guerillaglassWrote 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/okikesolutions/guerillaglass/guerilla-editing)<a href="https://agentmods.dev/skills/okikesolutions/guerillaglass/guerilla-editing"><img src="https://agentmods.dev/badge/skills/okikesolutions/guerillaglass/guerilla-editing/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/okikesolutions/guerillaglass/guerilla-editing"><img src="https://agentmods.dev/badge/skills/okikesolutions/guerillaglass/guerilla-editing.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 | $0.00037 | $0.00444 |
| Opus 5.5 | $0.00015 | $0.00178 |
| Sonnet 5.5 | $0.00007 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
guerilla-editing 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 today.
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.
What it actually says
Use the local engine and saved-project workflow. Read docs/AGENT_EDITING_RUNBOOK.md for project ownership and CLI operations. Close the desktop application before CLI project access. Each agent receives a fresh saved-project revision, the brief, and inspected source frames.
- Prepare a workspace with
bun run agent:workflow prepare <project> <brief.md> <workspace>. Inspectreview.jsonand the sampled source images. View the source recording around proposed cuts when samples are insufficient. Samples establish orientation, not proof that an entire scene is usable. - Hand the prepared workspace to a storyboard agent using storyboard instructions. That agent completes
storyboard.jsonwith exact source ranges and scene intent. It leaves the project unchanged. - Hand the storyboard to a separate editing agent using editing instructions. That agent compiles/validates the proposal, applies through the authorized CLI or submits it for desktop review, then renders the saved edit.
- Inspect the rendered video and its sampled frames. Write scene-specific feedback with
EditRenderReviewfrompackages/engine-contract/src/domains/editWorkflow.ts, then record it withagent:workflow record-review. Approval requires reviewing the video, not only successful encoding or samples. Mark requested changes against retained scene IDs. - For a revision, prepare a new workspace from the latest saved project and the user's correction brief. Pass the prior storyboard, render review, and fresh snapshot to the storyboard agent. Retain unchanged scene IDs and camera curves. Repeat editing and review until the brief is met or a concrete limitation needs the user.
Stop a pass on invalid plans, source mismatches, busy projects, or stale revisions. Inspect the current project before rebasing. Keep proposals, render receipts, and feedback in separate workspaces so a later pass cannot overwrite earlier evidence. Never label an uninspected render approved. LLM providers and orchestration remain external to the app.
What ships with it
2 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.
- today First seen · 15 lines · 37 tokens per session scan A 6e596a06f8b7
guerilla-editing is a skill published in the GitHub repository okikeSolutions/guerillaglass (10 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 444 once invoked, about $0.0001 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 2026-11-08.
guerilla-editing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| guerilla-editingokikeSolutions/guerillaglass | Skill | 10 | yesterday | MIT | A | 37 | Claude Code, Codex |
| skill-slimmingLearnPrompt/carl-skills | Skill | 77 | 3d ago | MIT | A | 182 | Codex |
| carl-file-organizerLearnPrompt/carl-skills | Skill | 77 | 3d ago | MIT | A | 216 | Codex |
| wechat-article-video-downloadLearnPrompt/carl-skills | Skill | 77 | 3d ago | MIT | A | 81 | Codex |
| video-add-captionsWhiteTowerAI/cut-as-code | Skill | 30 | 3d ago | MIT | A | 61 | Claude Code, Codex |
| video-add-content-cardsWhiteTowerAI/cut-as-code | Skill | 30 | 3d ago | MIT | A | 48 | Claude Code, Codex |
| video-to-shortsWhiteTowerAI/cut-as-code | Skill | 30 | 3d ago | MIT | A | 37 | Claude Code, Codex |