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/zhyx12/projtool/exp-statusgit clone --depth 1 https://github.com/zhyx12/projtoolWhat 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 | $0.00014 | $0.00469 |
| Opus 5 | $0.00007 | $0.00234 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
exp-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 2d 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.
What it actually says
You are running the user's /exp-status command. Produce a compact dashboard,
not a wall of text.
Steps
- Call
mcp__projtool__list_syncs— get mutagen session health. - Call
mcp__projtool__list_runsfiltered to runs whose manifeststatusisrunningor finished within the last 24h. - Call
mcp__projtool__worktree_statusfor the active worktree. - (Cheap, optional) call
mcp__projtool__diagnoseonly if any of the above surfaces something off — don't run a full diagnose if everything is green.
Output format
Print one short table for instances/syncs and one for recent runs. Use the following structure (markdown):
### Instances
| experiment | state | uuid | ssh alias |
|--------------|----------|--------|-----------------|
| exp-layernorm| bound | i-abc..| autodl-layernorm|
### Syncs
| name | status | last_event |
|------------------|-------------|------------|
| outputs | watching | 2m ago |
| layernorm-code | watching | 30s ago |
### Runs (active or recent)
| run_id | status | metric_summary |
|---------------------------------|-----------|-------------------|
| exp-layernorm/2026-05-08T22:14Z | running | epoch 12/40 |
| exp-baseline/2026-05-08T18:01Z | completed | best_val_acc=0.873|
If something is unhealthy (sync paused, manifest stale, instance disappeared
from AutoDL but binding says bound), call it out beneath the table with a
recommended fix (often sync_resume or refresh_ssh).
What NOT to do
- Don't list manifests in full — a one-line summary per run is enough.
- Don't fetch every run from history. Cap at the most recent ~10.
- Don't hand-roll ssh / git / mutagen commands; use the MCP tools.
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.
- 2d ago First seen · 49 lines · 14 tokens per session scan A 8f900ec17649
exp-status is a command published in the GitHub repository zhyx12/projtool (1 stars, last pushed 19d ago), licensed MIT. It adds 14 tokens to every session and 469 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.