Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. 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/friedbotstudio/baseline/main/.claude/skills/memory-sync/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/friedbotstudio/baseline/memory-sync)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/memory-sync"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/memory-sync/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/friedbotstudio/baseline/memory-sync"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/memory-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 302 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00099 | $0.05439 |
| Opus 5.5 | $0.00040 | $0.02176 |
| Sonnet 5.5 | $0.00020 | $0.01088 |
| Haiku 4.5 | $0.00010 | $0.00544 |
Grade A, and why
memory-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 1mo 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When invoked as a workflow phase (Phase 10.7)
This skill runs as Phase 10.7 of every committing workflow track (intake / spec / tdd / chore), between /roadmap-sync (Phase 10.6) and /grant-commit (Phase 11). The harness loop reads .claude/memory/_pending.md body, runs Step 0 canonical sweeps unconditionally, and on empty pending (zero ## CANDIDATE: blocks) short-circuits the fast-path: Steps 1–5 are skipped, Step 6 emits a one-line "no pending candidates" report, and the skill returns success. This keeps the no-op cost bounded at ≤ 3 sweep.mjs invocations per Phase 10.7 invocation.
The skill is also user-invokable outside the workflow (ad-hoc curation). When invoked ad-hoc and _pending.md is non-empty, the full Steps 1–5 flow runs identically. The fast-path activates per-invocation based on _pending.md body state, not on workflow context.
/commit (Phase 11) refuses to proceed unless memory-sync is in workflow.json → completed (or in exceptions). Empty-pending fast-path still appends "memory-sync" to completed — the prereq is satisfied either way.
(See "Method" below for the full Step 0 / Steps 1–5 / Step 6 flow.)
memory-sync — curate auto-extracted memory candidates
The memory_stop.mjs hook appends candidates to .claude/memory/_pending.md after every turn. This skill reviews them in main context (where conversation richness is preserved), commits the keepers to the right canonical file with proper metadata, and resets the pending body.
The hook is a passive collector. You are the curator. Discard noise, promote signal, deduplicate against existing canonical entries.
Inputs
.claude/memory/_pending.md— the pending body. Each block looks like:## CANDIDATE: <key> → <target-file>.md - field: value - field: value- The seven canonical files at
.claude/memory/<name>.md. Read each before deciding where a candidate lands and whether it duplicates existing content.
Method
Step 0 — Canonical sweep (closure semantics)
What ships with it
10 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.
- 1mo ago First seen · 308 lines · 99 tokens per session scan A 142de1e43e17
memory-sync is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It adds 99 tokens to every session and 5,439 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 2026-08-30.
Other skills, from other repositories
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
kb-answer
Answer questions using your project's knowledge base with evidence-backed citations. Every answer must cite literal quotes from KB files to prevent hallucinations. Use this for any question that should be answered from documented knowledge rather than general knowledge.
kb-import
Import knowledge from existing documents into structured KB entries. Reads source documents (Markdown, PDF, DOCX, plain text), extracts key information, and creates properly formatted KB entries with YAML frontmatter.
kb-refresh
Add new sources to your knowledge base or re-scrape existing ones to pick up changes. Supports Notion, Slack, Confluence, and local files. Can be run anytime after /setup-knowledge-base.