log-reflect

log-reflect is a skill for Claude Code, Codex from sunling/log-reflect-mcp. It costs 60 tokens per session (450 once invoked), scanned A, original, MIT.

A personal journal and notes workflow for saving, finding, and reviewing entries about experiences or outside material.

In plain words
What is it for?
Use it to record diary entries or notes about articles, books, podcasts, videos, conversations, quotations, links, and ideas.
Why use it?
It keeps personal reflections, ideas, and source notes organized and searchable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to record diary entries or notes about articles, books, podcasts, videos, conversations, quotations, links, and ideas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sunling/log-reflect-mcp/log-reflect
Install

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.

Any agent
npx skills add sunling/log-reflect-mcp --skill log-reflect
Clone the repo
git clone --depth 1 https://github.com/sunling/log-reflect-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for log-reflect

README.md
[![agentmods](https://agentmods.dev/badge/skills/sunling/log-reflect-mcp/log-reflect/github.svg)](https://agentmods.dev/skills/sunling/log-reflect-mcp/log-reflect)
Your own site
<a href="https://agentmods.dev/skills/sunling/log-reflect-mcp/log-reflect"><img src="https://agentmods.dev/badge/skills/sunling/log-reflect-mcp/log-reflect/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.

agentmods 80×15 button for log-reflect

Your own site · 80×15
<a href="https://agentmods.dev/skills/sunling/log-reflect-mcp/log-reflect"><img src="https://agentmods.dev/badge/skills/sunling/log-reflect-mcp/log-reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00450
Opus 5.5 $0.00024 $0.00180
Sonnet 5.5 $0.00012 $0.00090
Haiku 4.5 $0.00006 $0.00045

Measured 2mo ago against content hash c0852c868726, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

log-reflect 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 2mo 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.

skills/log-reflect/SKILL.md · 37 lines

What it actually says

Log Reflect

Use the connected Log Reflect tools as the source of truth for personal records.

Route the request

  • Use capture_journal for the user's lived experience, events, feelings, observations, or daily reflection.
  • Use capture_input for articles, books, podcasts, videos, courses, conversations, quotations, links, or ideas prompted by outside material.
  • Use get_records_by_date_range before weekly, monthly, or other period reviews.
  • Use search_records when the user asks whether, when, or how they previously mentioned a topic, person, feeling, event, or idea.
  • Infer journal versus input when the distinction is clear. Ask a short question only when the classification materially changes the saved record.

Preserve the user's voice

  • Lightly edit for readability, but retain uncertainty, unfinished thoughts, concrete details, and the user's own wording.
  • Never invent lessons, conclusions, emotions, tags, sources, or context.
  • Use the current date in the user's configured time zone unless they specify another date.
  • Choose a short factual title and a compact filename keyword.
  • For inputs, keep source material distinguishable from the user's personal response. Include a source URL or title when available and use no more than three useful tags.

Read and review

  • Resolve relative date phrases into an explicit inclusive date range before reading.
  • Ground summaries and patterns only in returned records. Distinguish direct evidence from interpretation.
  • If search results are insufficient, refine the query or date range instead of guessing.
  • Mention relevant dates or paths so the user can locate the underlying Markdown files.
  • Do not write a new record during a review unless the user explicitly asks to save it.

Confirm writes

After a successful write, briefly confirm whether the file was created or appended and show its repository-relative path. Never store credentials, access tokens, or unrelated private content.

Changes

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.

  1. 2mo ago First seen · 37 lines · 60 tokens per session scan A c0852c868726

Subscribe to this mod's changes

log-reflect is a skill published in the GitHub repository sunling/log-reflect-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 450 once invoked, about $0.0002 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 2026-08-31.

Related

log-reflect compared with skills from other repositories

log-reflect next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
log-reflectsunling/log-reflect-mcpSkill02mo agoMITA60Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code