sl

A command for loading and summarising recent session logs, which are saved records of earlier coding work.

In plain words
What is it for?
Use it to review recent project and coding-session history before continuing a task.
Why use it?
It restores context from previous sessions so work can continue without starting from the beginning.

Command for Claude Code

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.

agentmods
npx agentmods add commands/fwornle/coding/sl
Clone the repo
git clone --depth 1 https://github.com/fwornle/coding

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,271 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00014 $0.02271
Opus 5 $0.00007 $0.01136
Sonnet 5 $0.00003 $0.00454
Haiku 4.5 $0.00001 $0.00227

Measured yesterday against content hash cf5cf5ad5f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

sl scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

user-level rules in `~/.claude/settings.json`:
.claude/commands/sl.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Logs (/sl) - Session Continuity Command

Load and summarize recent Live Session Logs (LSL) to provide continuity from previous work sessions.

Instructions

Goal: Load recent LSL files and produce a summary to establish context continuity.

Tooling Rules (read first — these keep /sl prompt-free)

Use exactly the two ls forms below for discovery, and Read for content. Nothing else.

Do NOT use Glob. Claude Code no longer exposes a Glob tool to the main agent — search is done through Bash. An earlier version of this skill mandated Glob and banned Bash outright, which made every /sl run open with an apology about the preferred tool being unavailable before falling back to an ad-hoc find. The two commands below are the replacement; they are pre-allowed, so they do not prompt.

The two allowed discovery commands (<ROOT> is .specstory/history for the current project, or the absolute coding path for Step 3):

ls -d <ROOT>/[0-9][0-9][0-9][0-9]/[0-9][0-9]      # list YYYY/MM tranche dirs, oldest→newest
ls -1r <ROOT>/<YYYY>/<MM>                          # list one month's files, NEWEST FIRST

Both are matched by user-level allow rules (see Permissions), so they run prompt-free in any project.

Two things the numeric [0-9] pattern buys you — do not "simplify" it away:

  • .specstory/history also contains non-LSL subtrees (logs/, docs/). A recursive **/*.md sweep over the coding project returns ~23,000 files, almost all noise. The numeric year/month pattern selects only real LSL tranches.
  • Listing one month at a time keeps the result at tens of files, not thousands.

Never reach for these — each one triggers a prompt even where a matching Bash(...) allow rule exists, because the permission matcher cannot statically resolve the command it runs:

  • find … -exec <cmd> (the -exec payload is opaque to the matcher)
  • xargs <cmd> / `cmd` / $(cmd) (nested command)
  • pipelines (ls … | head, find … | sort) — every stage needs its own allow rule, and the project-scoped ones only exist in coding

Read the full file on GitHub · 194 lines

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. yesterday First seen · 194 lines · 14 tokens per session scan B cf5cf5ad5f25

Subscribe to this mod's changes

sl is a command published in the GitHub repository fwornle/coding (2 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 2,271 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.