A project note-taking system that keeps a chronological DEVLOG.md and a reusable LESSON.md. The first records what happened, while the second organizes problems, causes, and solutions for later reference.

For recording coding work, architecture decisions, non-trivial bug fixes, and library lessons in local-only project files.

It prevents important decisions, bug fixes, and technical discoveries from being lost or mixed into a temporary task list.

How Echoqili/ssh-licco configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to Echoqili/ssh-licco. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Echoqili/ssh-licco/master/.trae/skills/devlog/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Echoqili/ssh-licco

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/echoqili/ssh-licco/devlog/github.svg)](https://agentmods.dev/skills/echoqili/ssh-licco/devlog)

Your own site

<a href="https://agentmods.dev/skills/echoqili/ssh-licco/devlog"><img src="https://agentmods.dev/badge/skills/echoqili/ssh-licco/devlog/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/echoqili/ssh-licco/devlog"><img src="https://agentmods.dev/badge/skills/echoqili/ssh-licco/devlog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,936 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.

Model	Per session	Once invoked
Fable 5.1	$0.00157	$0.03936
Opus 5.5	$0.00063	$0.01574
Sonnet 5.5	$0.00031	$0.00787
Haiku 4.5	$0.00016	$0.00394

Measured 2mo ago against content hash 2eff564cfe33, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

devlog 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/setup.ps1, scripts/setup.sh, scripts/verify-ignored.ps1, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.trae/skills/devlog/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEVLOG Skill

Maintain two local-only project files that work together:

File	Role	Style
`DEVLOG.md`	Chronological log of what was done, planned, and learned	Append-only, dated entries
`LESSON.md`	Aggregated knowledge base of problems → root causes → solutions	Indexed, category-organized, reusable

Rule of thumb: DEVLOG.md records the journey; LESSON.md records the wisdom.

Both files are local-only — they must never reach the remote repository, and the ignore rules for them must not be committed either. This is achieved with .git/info/exclude (a per-repo, never-tracked file), not .gitignore.

When to Use

Invoke this skill when any of the following happen:

Starting a new coding task in a project
Completing a coding task or a significant sub-step
Making an architectural or design decision
Fixing a non-trivial bug
Discovering a library / framework gotcha
User says things like "log this", "记一下", "记到 DEVLOG", "记到 LESSON", "做个总结", "加到 LESSON", "save a lesson", "remember this gotcha"

When NOT to Use

Short-lived TODOs — use the project issue tracker or a local TODO file.
Public-facing documentation — use the project wiki or a shared doc.
Free-form chat summaries — use conversation search, not a log file.
Secrets, credentials, or PII — never store in either file, even though they are local.
One-line trivial commits — skip; only log meaningful changes.

First-Run Setup

On first invocation in a project (or if either file is missing):

Run the platform-appropriate setup script — it creates both files from templates and registers them in .git/info/exclude:
```
# POSIX (bash, zsh, Git Bash, WSL)
./.trae/skills/devlog/scripts/setup.sh
```
```
# Windows PowerShell 5+
./.trae/skills/devlog/scripts/setup.ps1
```
The script is idempotent — safe to re-run.
Verify with: git check-ignore -v -- DEVLOG.md LESSON.md
- Expected: both lines reference .git/info/exclude.

Read the full file on GitHub · 387 lines

Files

What ships with it

6 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.

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.

2mo ago First seen · 387 lines · 157 tokens per session scan A 2eff564cfe33

Subscribe to this mod's changes

devlog is a skill published in the GitHub repository Echoqili/ssh-licco (4 stars, last pushed 11d ago), licensed MIT. It adds 157 tokens to every session and 3,936 once invoked, about $0.0006 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.

Memory and context Writing and docs

devlog next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
devlogEchoqili/ssh-licco	Skill	4	11d ago	MIT	A	157	Claude Code, Codex
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	74	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex

ssh-licco: Skill for Claude Code