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 jleechanorg/agent-orchestrator-ts --skill tmux-video-evidencegit clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-tsWrote 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/jleechanorg/agent-orchestrator-ts/tmux-video-evidence)<a href="https://agentmods.dev/skills/jleechanorg/agent-orchestrator-ts/tmux-video-evidence"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/tmux-video-evidence/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/jleechanorg/agent-orchestrator-ts/tmux-video-evidence"><img src="https://agentmods.dev/badge/skills/jleechanorg/agent-orchestrator-ts/tmux-video-evidence.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 | $0.00021 | $0.01463 |
| Opus 5.5 | $0.00008 | $0.00585 |
| Sonnet 5.5 | $0.00004 | $0.00293 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
tmux-video-evidence scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tmux Video Evidence for Agent Work Verification
Purpose
Record terminal-based evidence videos that another agent (or human) can review to verify that code changes, test results, and deployments are legitimate. The key principle: the video must tie test output to a specific git commit and prove no tampering occurred during recording.
Prerequisites
# Required
brew install asciinema # Terminal recorder (outputs .cast files)
brew install agg # Converts .cast → .gif for embedding in docs/PRs
Evidence Script Template
Create a script at /tmp/<work_name>_evidence.sh:
#!/bin/bash
# Evidence Recording Script — <PR/Work Item>
set -e
REPO_ROOT="<absolute path to repo>"
cd "$REPO_ROOT"
echo "╔═══════════════════════════════════════════════════════╗"
echo "║ <Title> — Evidence Capture ║"
echo "║ Recorded: $(date -u '+%Y-%m-%dT%H:%M:%SZ') ║"
echo "╚═══════════════════════════════════════════════════════╝"
echo ""
# ── 1. Git Provenance (MANDATORY — ties ALL output to this commit) ──
echo "━━━━━━━ 1. GIT PROVENANCE ━━━━━━━"
HEAD_SHA=$(git rev-parse HEAD)
BRANCH=$(git branch --show-current)
echo " HEAD SHA: $HEAD_SHA"
echo " Branch: $BRANCH"
echo " Merge-base vs main: $(git merge-base HEAD origin/main)"
echo " Commits ahead of main: $(git rev-list --count origin/main..HEAD)"
echo ""
# ── 2. Commit log ──
echo "━━━━━━━ 2. COMMIT LOG ━━━━━━━"
git log --oneline origin/main..HEAD
echo ""
# ── 3. Actual code diffs (not just --stat) ──
echo "━━━━━━━ 3. CODE DIFFS ━━━━━━━"
echo "--- diff --stat ---"
git diff --stat origin/main...HEAD
echo ""
echo "--- key file diffs (abbreviated) ---"
# Show actual diff for each important file:
for f in <list important changed files>; do
echo "[$f]:"
git diff origin/main...HEAD -- "$f" | head -60
echo ""
done
# ── 4. PR/Work Item verification ──
echo "━━━━━━━ 4. PR STATUS ━━━━━━━"
gh pr view <PR_NUMBER> --json number,title,url,headRefName,state \
-q '{number, title, url, headRefName, state}'
echo ""
# ── 5. Live test execution ──
echo "━━━━━━━ 5. LIVE TEST EXECUTION ━━━━━━━"
echo "Running tests against commit $HEAD_SHA..."
# Run your test suites:
cd "$REPO_ROOT/<package>"
npm test 2>&1 | grep -E "(PASS|FAIL|Test Suites|Tests:|Time:)"
echo ""
# ── 6. Post-test SHA check (MANDATORY — proves no commit change) ──
echo "━━━━━━━ 6. POST-TEST SHA VERIFICATION ━━━━━━━"
cd "$REPO_ROOT"
POST_SHA=$(git rev-parse HEAD)
echo " Pre-test SHA: $HEAD_SHA"
echo " Post-test SHA: $POST_SHA"
if [ "$HEAD_SHA" = "$POST_SHA" ]; then
echo " ✅ SHA MATCH — tests ran against the claimed commit"
else
echo " ❌ SHA MISMATCH — working tree changed during tests!"
fi
echo " Working tree clean: $(git status --porcelain | wc -l | tr -d ' ') uncommitted changes"
echo ""
echo "╔═══════════════════════════════════════════════════╗"
echo "║ EVIDENCE COMPLETE — Commit: $HEAD_SHA ║"
echo "╚═══════════════════════════════════════════════════╝"
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.
- 9d ago First seen · 162 lines · 21 tokens per session scan A 36bfbeb23302
tmux-video-evidence is a skill published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 1,463 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 2026-10-02.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…