sle

A command that reports how long work items usually take, using historical cycle-time percentiles.

In plain words
What is it for?
Use it to view the 50th, 70th, 85th, and 95th percentile completion times, optionally filtered by author or repository.
Why use it?
It turns past delivery data into time ranges, while warning when too little data is available for dependable results.

Command

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/tommymorgan/claude-plugins/sle
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00011 $0.00477
Opus 5 $0.00005 $0.00238
Sonnet 5 $0.00002 $0.00095
Haiku 4.5 $0.00001 $0.00048

Measured 2d ago against content hash df7b73dfb306, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sle 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 2d 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.

flow/commands/sle.md · 47 lines

What it actually says

Flow SLE (Service Level Expectations)

Show Cycle Time percentile lines from historical flow data.

Steps

  1. Resolve project config by matching git remote URL against ~/.tommymorgan/flows/

    • If no config: "No flow configuration found for remote URL: . Run /flow:setup to configure."
    • If invalid config: "Configuration file is invalid: . Run /flow:setup to reconfigure."
  2. Read flow data from ~/.tommymorgan/flows/<slug>-data.json

    • If no data: "No flow data found. Run /flow:fetch-data first."
  3. Apply filters if provided (--author, --repo)

  4. Check sample size:

    • If fewer than 20 data points: "Warning: Only {count} data points available (minimum 20 recommended for reliable percentiles). Results may not be representative."
    • Display results regardless (don't block)
  5. Calculate percentiles at 50th, 70th, 85th, and 95th using rank-based ordering

  6. Display:

    Service Level Expectations ({count} items, {date_range})
    {filter_description if filtered}
    
    50th percentile:  {n} days — 50% of items finish in {n} days or less
    70th percentile:  {n} days — 70% of items finish in {n} days or less
    85th percentile:  {n} days — 85% of items finish in {n} days or less
    95th percentile:  {n} days — 95% of items finish in {n} days or less
    

Arguments

  • --author <name> — Filter to a specific author
  • --repo <owner/repo> — Filter to a specific repo

Important

  • These are calendar days (no weekends subtracted)
  • Percentiles are forecasts: "85th percentile = 12 days" means "there is an 85% chance the next item will finish in 12 days or less"
  • Never communicate these as averages
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. 2d ago First seen · 47 lines · 11 tokens per session scan A df7b73dfb306

Subscribe to this mod's changes

sle is a command published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 477 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.