Borrowing it
Nothing to install: this file belongs to HelgDemidov/refigure. 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/HelgDemidov/refigure/main/.claude/commands/post-merge-sync.mdgit clone --depth 1 https://github.com/HelgDemidov/refigureWrote 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/helgdemidov/refigure/post-merge-sync)<a href="https://agentmods.dev/commands/helgdemidov/refigure/post-merge-sync"><img src="https://agentmods.dev/badge/commands/helgdemidov/refigure/post-merge-sync.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 5.1 | $0.00019 | $0.00854 |
| Opus 5 | $0.00010 | $0.00427 |
| Sonnet 5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
post-merge-sync 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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync project documentation and long-term memory after a successful PR merge into main.
Run git log main --oneline -15 and git diff HEAD~1 --stat to understand what changed.
Then perform ALL of the following steps — in order, without skipping:
Step 1 — Update CLAUDE.md (repo root)
Read the current CLAUDE.md. Update ONLY sections that are factually outdated based on the merged changes:
- New modules landing in
refigure/(e.g.docx.py,xlsx.py,chart_data.pyported) - New/changed extras in
pyproject.toml([docx],[xlsx],[vlm]) - Changes to commands, dependency versions, or dev tooling
- New architectural constraints or "Do NOT" rules
Do NOT add micropatterns or implementation details — only architectural/infrastructure facts. Keep the file under 100 lines.
Step 2 — Update or create memory files
Read the current MEMORY.md index at the project memory path.
For each significant change in the merged PR, decide:
- New subsystem or feature → create
project_<feature>.md(type: project) - Architectural decision with lasting consequences → create or update
project_*.md - Testing/tooling lesson learned → create or update
feedback_*.md - New external resource or reference → create
reference_*.md
Memory body structure: lead with the fact/rule, then Why: and How to apply: lines.
Update MEMORY.md index: add one line per new file, update description of changed files.
Step 3 — Update spec status
If the merge closes a feature branch with a spec at docs/<category>/<slug>/<slug>-<date>.md AND that file still exists in this local checkout (docs/ is gitignored since 2026-08-19 — the spec was never committed/pushed by /tech-spec, so it only exists if you're running this on the same machine that drafted it; if it's missing, skip this step, there's nothing to update), append a concise §"Статус выполнения" section (10–15 lines) stating: merge date, PR number, commit hashes, what was done, what remains out of scope. Like Step 1/2, this edit is made in place on disk but is NEVER staged or committed — it's local-only bookkeeping now, not a shared repo artifact.
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.
- 6d ago First seen · 49 lines · 19 tokens per session scan A 024d75517ed8
post-merge-sync is a command published in the GitHub repository HelgDemidov/refigure (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 854 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 commands, from other repositories
worktree-start
Set up an isolated worktree so you can work on a branch without affecting other agents or the main checkout.
index-cmd
The index command reindexes a repository and synchronizes its anchor ledger while selecting human-readable, JSON, or quiet output.
changelog
Reads git log since the last tag (or all history), groups commits by type, and generates or updates CHANGELOG.md following the Keep a Changelog format.
commit-msg
Reads the current git diff (staged and unstaged changes), analyzes what changed, and suggests a Conventional Commits-compliant commit message.
pr-desc
Reads git diff between the current branch and main (or a specified base branch), analyzes changed files, and generates a structured pull request description ready to paste into GitHub.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.