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 avelikiy/great_cto/plugin install great-ctoWrote 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/commands/avelikiy/great_cto/resume)<a href="https://agentmods.dev/commands/avelikiy/great_cto/resume"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/resume/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/commands/avelikiy/great_cto/resume"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/resume.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 | $0.00029 | $0.01656 |
| Opus 5 | $0.00015 | $0.00828 |
| Sonnet 5 | $0.00006 | $0.00331 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
resume scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great_cto /resume command. Your job is to restore full session context in under 60 seconds so the CTO can continue exactly where they left off — without re-explaining the project, stack, or pending work.
Step 1 — Collect context (run all in parallel)
# Project identity
cat .great_cto/PROJECT.md 2>/dev/null || echo "NO_PROJECT"
# Recent session logs (last 3)
ls -t .great_cto/logs/session-*.md 2>/dev/null | head -3
# RELEVANT past sessions (BM25 ranked, not just recent) — query = current branch
# + open task titles, so resuming to work on X surfaces the X sessions even if
# they aren't the newest. Fail-open: silent if node/module unavailable.
MS="${CLAUDE_PLUGIN_ROOT:-$(ls -d "$HOME"/.claude/plugins/cache/*/great_cto/*/ 2>/dev/null | sort -V | tail -1 | sed 's|/$||')}/scripts/lib/memory-search.mjs"
if command -v node >/dev/null 2>&1 && [ -f "$MS" ]; then
RQ="$(git branch --show-current 2>/dev/null) $(bd list --status open 2>/dev/null | head -5 | sed 's/^[^ ]* //' | tr '\n' ' ')"
[ -n "$(echo "$RQ" | tr -d ' ')" ] && { echo "# Relevant past sessions (ranked):"; node "$MS" "$RQ" --source logs --limit 4 2>/dev/null; }
fi
# Open tasks (Beads or tasks.md)
cat .great_cto/tasks.md 2>/dev/null | grep -E "^\- \[ \]|^## " | head -20
# Recent decisions
tail -60 docs/decisions/DECISION-LOG.md 2>/dev/null || echo "NO_DECISION_LOG"
# Latest ADR
ls -t docs/adr/ADR-*.md 2>/dev/null | head -1 | xargs head -20 2>/dev/null
# Open gates
find .great_cto/verdicts -name "*.md" 2>/dev/null | xargs grep -l "status: open\|OPEN\|pending" 2>/dev/null | head -5
# Pipeline stage state — WHERE the interrupted run stopped.
# An interrupted run keeps its code (it is committed) but loses its place, so a
# resume either redoes finished stages or skips unfinished ones and ships. This
# reconstructs the answer from the verdict logs instead of the operator having to
# hand-write "these stages are done" into the resume prompt. Exit 3 = a mandatory
# stage (QA / security) still has no terminal verdict.
_PS=$(ls ~/.claude/plugins/cache/*/great_cto/*/scripts/pipeline-state.mjs 2>/dev/null | sort -V | tail -1)
[ -z "$_PS" ] && _PS="scripts/pipeline-state.mjs"
[ -f "$_PS" ] && node "$_PS" . 2>/dev/null || echo "NO_PIPELINE_STATE"
# Git: last 5 commits
git log --oneline -5 2>/dev/null || echo "NO_GIT"
# Git: what's dirty / in progress
git status --short 2>/dev/null | head -10
# Open PRs
gh pr list --state open --limit 5 --json number,title,reviewDecision 2>/dev/null | python3 -c "import json,sys; prs=json.load(sys.stdin); [print(f'PR #{p[\"number\"]}: {p[\"title\"]} [{p.get(\"reviewDecision\") or \"pending\"}]') for p in prs]" 2>/dev/null || true
# Graphify graph (if present)
[ -f graphify-out/GRAPH_REPORT.md ] && head -20 graphify-out/GRAPH_REPORT.md || true
Read the 3 most recent session logs:
for LOG in $(ls -t .great_cto/logs/session-*.md 2>/dev/null | head -3); do
echo "=== $LOG ==="
cat "$LOG"
echo ""
done
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.
- 2d ago Changed 8342afcbc858
- 6d ago First seen · 181 lines · 29 tokens per session scan A c375d7420420
resume is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,656 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 2026-09-03.
Other commands, from other repositories
develop
Implement skill development issues with TDD-governed workflow.
rust-teach
One-time setup that scans your Rust project, understands its patterns and conventions, and writes a Rust-specific context section to your CLAUDE.md. Run once per project to establish persistent Rust guidelines.
discover-genius
Excavate genius from a person's scattered corpus. Produces Genius Profile (what only they uniquely see) + Freedom Path (four-bucket sort of every activity). Gateway to all downstream intelligence systems. For humans, not agents.
fec-doc-sync
Sync README, docs, environment variables, scripts, API/routing/component descriptions and deployment instructions from code and project sources of truth.
pin
Break checkpoint — status display, session log, optional MEMORY.md update.
design-review
Compare design (Figma URL or mockup image) against implementation to detect UI mismatches (colors, layout, typography).