Borrowing it
Nothing to install: this file belongs to philngt/contextd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/philngt/contextd/main/.claude/commands/contextd-admin.mdgit clone --depth 1 https://github.com/philngt/contextdWrote 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/philngt/contextd/contextd-admin)<a href="https://agentmods.dev/commands/philngt/contextd/contextd-admin"><img src="https://agentmods.dev/badge/commands/philngt/contextd/contextd-admin/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.
<a href="https://agentmods.dev/commands/philngt/contextd/contextd-admin"><img src="https://agentmods.dev/badge/commands/philngt/contextd/contextd-admin.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00615 |
| Opus 5.5 | $0.00000 | $0.00246 |
| Sonnet 5.5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
contextd-admin 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 1mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/contextd-admin — Admin & Diagnostics Index
Single entry point that explains the engine-administration slash commands. These commands operate on contextd itself (install metadata, backups, pipeline traces, evals) — not on workspace knowledge or user tasks.
Use this file when you're not sure which admin command you need. Each command is still callable directly; this is only a navigation aid.
Quick map
| Goal | Command |
|---|---|
| Show installed version + release tag | /contextd-version |
| Confirm contextd is installed and resolve its wiki root | /contextd-detect |
| Upgrade to latest release | /contextd-upgrade |
| Snapshot active workspace into a backup archive | /contextd-backup |
| Restore a workspace from a backup archive | /contextd-restore |
| Render workspace status / coverage report | /contextd-report |
| Inspect a single pipeline trace (intent → retrieval → validate) | /contextd-trace |
| Visualize pipeline traces in an HTML viewer | /contextd-viz |
| Run A/B eval over golden tasks | /contextd-eval |
| Explain a concept (workspace / pack / contract / pipeline term) | /contextd-explain |
When to reach for these
- Install / upgrade / detect / version: setting up a new machine, bumping to a new release, troubleshooting "command not found".
- Backup / restore: before a risky rebase, or migrating a workspace between machines.
- Report / trace / viz / eval: debugging "why did the agent pull the wrong context" or running prompt-pipeline regression.
- Explain: when the user (or you) is unsure what a wiki concept means.
Task commands live elsewhere
These are not admin commands — they are the commands you reach for during actual work:
/use-contextd— frame a new task against the active workspace/update-contextd— sync wiki after code changes/rebase-contextd— rebuild wiki snapshot against current code/contextd-setup— first-time per-codebase setup/switch-workspace,/list-workspaces,/new-workspace/code-analyze,/evidence-{ingest,analyze,qa,apply},/obsidian-ingest/product-brief,/business-view,/tool-design,/tool-extend,/tool-list/find,/suggest-automation,/observations-clear
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.
- 1mo ago First seen · 43 lines · 0 tokens per session scan A 9c7f4738f119
contextd-admin is a command published in the GitHub repository philngt/contextd (29 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 615 tokens. 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
bm
Ask basemind anything about the current codebase — outlines, refs, callers, git history, blame, diffs, docs, memory.
gaai-ask
Search workspace memory — ranked entries with 1-hop graph context (cognitive guarantee).
gaai-bootstrap
Initialize or refresh project context via Bootstrap Agent.
dream
Run a curator pass over the memory dir. Produces a proposal artifact for /dream-apply. Default curator: rot.
vault
Build/refresh a unified Obsidian vault (knowledge + all repo wikis).
moves
Explain the live KMP memory and ChronoLoom moves.