Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add danielLublinsky/Skill-Atlas/plugin install skill-atlasWrote 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/daniellublinsky/skill-atlas/edit-searchable)<a href="https://agentmods.dev/commands/daniellublinsky/skill-atlas/edit-searchable"><img src="https://agentmods.dev/badge/commands/daniellublinsky/skill-atlas/edit-searchable.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 5.1 | $0.00014 | $0.01090 |
| Opus 5 | $0.00007 | $0.00545 |
| Sonnet 5 | $0.00003 | $0.00218 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade A, and why
edit-searchable scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit the searchable tier: pick an action, pick the plugins, refresh.
A plugin is searchable only when BOTH halves hold — Claude Code has it
disabled (settings) and this scope opted it in (config.json). This
command owns both halves. The unit is a plugin, not a single skill: selecting
one moves all its skills together.
1. Read the current state
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/build_graph.py"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/categorize.py" config --list
Exit 1 is dangling defects elsewhere — carry on. Exit 2 is fatal: report
stderr and stop; if it names categories.json or config.json violations
that is curated state, so offer to fix it and NEVER regenerate it.
Show every plugin as a table — plugin, skills, tier — ordered searchable →
off → enabled. Mention any orphan_opt_ins (opt-ins naming no installed
plugin).
2. Ask the action — always
One AskUserQuestion, single-select. Ask it every time; never infer the action from the rollup, and never skip it because one direction looks empty:
- Add a plugin — move a plugin into the searchable tier
- Remove a plugin — take a plugin out of it
Put the candidate count in each description. ("Other" is offered automatically — honour whatever the user types there.) If the chosen action has no candidates, say so plainly and stop; do not substitute the opposite.
3. Multi-select the plugins
One AskUserQuestion, multiSelect: true, options = candidates for the chosen
action only:
- Add → plugins at tier
offfirst (already disabled — one call each), thenenabledones (these also need a disable). Give each option its skill count. Anenabledplugin going searchable saves ~48 tokens per skill per session; anoffplugin already costs nothing, so it gains findability, not tokens — don't present those as the same win. - Remove → the current
searchableplugins.
Max 4 options per question, 4 questions per call. If candidates exceed that, offer the highest-payoff ones and say which were not offered — never let a cap look like a complete list.
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.
- 8d ago First seen · 105 lines · 14 tokens per session scan A 176439c8c480
edit-searchable is a command published in the GitHub repository danielLublinsky/Skill-Atlas (23 stars, last pushed 22d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,090 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 2026-08-30.
Other commands, from other repositories
guide
Skill navigator -- explains all installed skills and slash commands in your language. Usage: /guide (overview), /guide (deep dive), /guide (recommendation), /guide --check (dependency check), /guide --diff (compare with a skill pack).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.