status

status is a command for Claude Code from jamditis/claude-skills-journalism. It costs 7 tokens per session (1,148 once invoked), scanned A, original, MIT.

A command that reports statistics about a project's local autocontext knowledge store, which records lessons learned from previous work. It reads lesson files, configuration, and pending cached entries when that store exists.

In plain words
What is it for?
Use it to inspect lesson counts by category, active and archived lessons, confidence metrics, and whether autocontext has been initialized for the project.
Why use it?
It gives a quick view of how much project knowledge has been collected and how it is categorized and rated for confidence.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the autocontext plugin — 5 commands, 1 agent shipped together

Good fit Use it to inspect lesson counts by category, active and archived lessons, confidence metrics, and whether autocontext has been initialized for the project.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jamditis/claude-skills-journalism/status
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.

Clone the repo
git clone --depth 1 https://github.com/jamditis/claude-skills-journalism

Made for: Claude Code.

Or install autocontext, the plugin that ships this one along with the rest of its 5 commands, 1 agent.

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 status

README.md
[![agentmods](https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/status/github.svg)](https://agentmods.dev/commands/jamditis/claude-skills-journalism/status)
Your own site
<a href="https://agentmods.dev/commands/jamditis/claude-skills-journalism/status"><img src="https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/status/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 status

Your own site · 80×15
<a href="https://agentmods.dev/commands/jamditis/claude-skills-journalism/status"><img src="https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,148 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 $0.00007 $0.01148
Opus 5 $0.00003 $0.00574
Sonnet 5 $0.00001 $0.00230
Haiku 4.5 $0.00001 $0.00115

Measured 10d ago against content hash a0c8f333eb50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

status 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 10d 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.

autocontext/commands/status.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Display stats and status for the autocontext in the current project.

Precondition

Before displaying stats, the script checks if .autocontext/ exists. If it doesn't, you'll see:

Autocontext not initialized for this project.
Run '/autocontext:init' to set up knowledge tracking.

Otherwise, the script reads:

  • .autocontext/lessons.json, active and archived lessons
  • .autocontext/config.json, project configuration
  • .autocontext/cache/, any pending lessons

Status report

The script displays a clean, organized report with the following sections:

1. Lessons by category

Breakdown of all lessons (active and tombstoned) by category:

Lessons by category:
  bug-fix:          12 active, 3 tombstoned
  architecture:     8 active, 1 tombstoned
  workflow:         15 active, 2 tombstoned
  pattern:          6 active, 0 tombstoned
  gotcha:           9 active, 1 tombstoned
  integration:      4 active, 0 tombstoned
  test-strategy:    5 active, 0 tombstoned

Total: 59 active lessons | 7 tombstoned

2. Confidence metrics

Average confidence across all active lessons:

Confidence metrics:
  Average confidence: 0.72
  High confidence (>= 0.8):  28 lessons
  Medium confidence (0.5-0.8):  26 lessons
  Low confidence (< 0.5):  5 lessons

3. Most-validated lessons

Top 5 lessons with the highest validated_count (most confirmed across sessions):

Most-validated lessons (by developer/session confirmations):
  1. [Architecture] "Split domain logic from infrastructure", validated 34 times
  2. [Workflow] "Always run tests before commit", validated 28 times
  3. [Bug-fix] "Regex patterns need raw strings", validated 22 times
  4. [Pattern] "Use dependency injection for testing", validated 18 times
  5. [Test-strategy] "Write integration tests for API changes", validated 16 times

4. Stalest lessons

Top 5 lessons with lowest confidence or oldest last_validated timestamp (need attention):

Stalest lessons (lowest confidence or oldest validation):
  1. [Workflow] "Use Docker for local dev", confidence 0.3, last validated 120 days ago
  2. [Integration] "Slack API batch operations", confidence 0.4, last validated 89 days ago
  3. [Gotcha] "Python timezone handling edge case", confidence 0.5, last validated 73 days ago
  4. [Architecture] "Consider microservices for X", confidence 0.4, last validated 95 days ago
  5. [Pattern] "SQL query optimization with indexes", confidence 0.5, last validated 67 days ago

Read the full file on GitHub · 158 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. 10d ago First seen · 158 lines · 7 tokens per session scan A a0c8f333eb50

Subscribe to this mod's changes

status is a command published in the GitHub repository jamditis/claude-skills-journalism (389 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 1,148 once invoked, about $0.0000 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 2026-08-30.