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.
npx agentmods add commands/hesreallyhim/ultracode-workflows/wf-statuslinegit clone --depth 1 https://github.com/hesreallyhim/ultracode-workflowsWrote 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.
[](https://agentmods.dev/commands/hesreallyhim/ultracode-workflows/wf-statusline)<a href="https://agentmods.dev/commands/hesreallyhim/ultracode-workflows/wf-statusline"><img src="https://agentmods.dev/badge/commands/hesreallyhim/ultracode-workflows/wf-statusline.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00012 | $0.00837 |
| Opus 5 | $0.00006 | $0.00418 |
| Sonnet 5 | $0.00002 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade B, and why
wf-statusline 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **user** → `~/.claude/settings.json` (every project) How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wf-statusline
Install the lightweight workflow-progress statusline. It renders observed running/done counts and elapsed time in the always-visible status row. If the richer run viewer has already cached a static phase plan, phase names appear as optional decoration:
⚡ docs-drift-audit · Inventory › Extract › Check › Fix · ●1 ✓8 8m46s
✔ deep-code-review · Scope✓ Review✓5 Verify✓8 Report✓ · 15⚙ 1.2M 4m10s
The script is at ${CLAUDE_PLUGIN_ROOT}/scripts/workflow-statusline.mjs.
Steps
-
Ask which scope they want, unless
$ARGUMENTSalready says:- project →
.claude/settings.jsonin the current project (this repo only) - user →
~/.claude/settings.json(every project)
- project →
-
Wire it up by editing that settings file yourself. Merge into the existing JSON — never overwrite the file, and preserve every other key:
{ "statusLine": { "type": "command", "command": "config_dir=\"${CLAUDE_CONFIG_DIR:-$HOME/.claude}\"; statusline_script=\"$(ls -t \"$config_dir\"/plugins/cache/ultracode-workflows/ultracode-workflows/*/scripts/workflow-statusline.mjs 2>/dev/null | head -n 1)\"; if [ -n \"$statusline_script\" ]; then exec node \"$statusline_script\"; fi", "padding": 0, "refreshInterval": 5 } }Write the resolver literally; do not expand its shell variables while editing the JSON. Claude Code installs marketplace plugins in versioned cache directories, so the command selects the most recently written valid copy on every render instead of persisting one version's path. Both marketplace and plugin directory names are exact; only the version directory is allowed to vary.
-
If a
statusLinealready exists, don't silently replace it. Show the user the current command and ask whether to replace it. (Composing two is possible — read stdin once, feed both — but only if they ask.) -
Verify the installed command renders before declaring success. Read the exact
statusLine.commandvalue back from the settings file and feed that command a sample of the JSON Claude Code pipes in. Do not test a different source path instead:
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.
- 4d ago First seen · 55 lines · 12 tokens per session scan B 672570062765
wf-statusline is a command published in the GitHub repository hesreallyhim/ultracode-workflows (2 stars, last pushed 28d ago), licensed MIT. It adds 12 tokens to every session and 837 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.
Other commands, from other repositories
no-cape
Manually load a no-cape discipline skill and apply it to the current work.
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
create-topic
Research and generate a complete topic plan with keyword mapping, audience, angle, and competitive positioning.
list
List the NeatContext contexts you can connect.