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/knitli/toolshed/ctxgit clone --depth 1 https://github.com/knitli/toolshedWhat 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 | $0.00024 | $0.01234 |
| Opus 5 | $0.00012 | $0.00617 |
| Sonnet 5 | $0.00005 | $0.00247 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
ctx 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 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.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ctx — Full Context Audit
Run a complete context hygiene audit: discover all AI context files, check them for staleness against the actual codebase, and detect drift/contradictions across tool boundaries.
Arguments
$ARGUMENTS
- No arguments: audit everything — full discovery, check all files, detect all drift.
- File paths (e.g.,
/ctx CLAUDE.md): scope all three phases to just those files. Discovery still runs (to build the full inventory for drift comparison), but staleness checking and drift detection focus on the named files. - Ecosystem names (e.g.,
/ctx cursor serena): scope to all context files belonging to those ecosystems (as defined in the INI).
Instructions
You are running a context hygiene audit on this repository. Complete all three phases in order, then produce a summary report. If the user provided arguments above, scope your work accordingly — but always run discovery first to establish the full context file inventory.
Phase 1: Discovery
Scan the repository for ALL AI context files using the plugin's authoritative ecosystem inventory at ${CLAUDE_PLUGIN_ROOT}/data/context-files.ini. Read that file first — it lists every ecosystem, root file, nested memory file, tool directory, config file, and ignore directory the plugin knows about. Any entry there is in scope; entries not there are not (unless caught by heuristics, below).
The INI currently covers ~15 ecosystems: Claude Code, universal AGENTS.md, Gemini, OpenAI Codex, Cursor, Windsurf, Continue, Roo/Cline, Crush, Aider, Serena, spec-kit, GitHub agents/skills, VS Code, and planning/output directories. See /ctx:discover for the full treatment.
Heuristic checks (beyond the INI's exact-match list):
- Any markdown file in repo root with an ALL_CAPS filename not in the
allcaps_excludelist under[heuristics]in the INI. - Symlinks between context files (e.g.,
GEMINI.md → CLAUDE.md). - Files containing phrases like "when working with this repo", "you are an AI", "assistant instructions" — these are often context files regardless of extension or location.
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.
- yesterday First seen · 86 lines · 24 tokens per session scan A 46a0928e6527
ctx is a command published in the GitHub repository knitli/toolshed (1 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,234 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.
Other commands, from other repositories
frappe-doctype-design
Handle this as Frappe DocType design work.
frappe-backend
Treat the task as Frappe backend work.
frappe-builder
Treat the task as Frappe Builder or website work.
frappe-crm
Treat the task as Frappe CRM work.
frappe-drive
Treat the task as Frappe Drive work.
frappe-fullstack
Act as a Frappe full-stack specialist.