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/eshwarvijay/secondmate/secondmate-doctorgit clone --depth 1 https://github.com/eshwarvijay/secondmateWhat 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 | $0.00047 | $0.00392 |
| Opus 5 | $0.00023 | $0.00196 |
| Sonnet 5 | $0.00009 | $0.00078 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
secondmate-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Set up secondmate end to end. YOU (the agent) run every fix so the human only approves it via the normal permission prompt — never make the human hunt for install steps.
- Detect:
bash "${CLAUDE_PLUGIN_ROOT}/bin/doctor.sh" --json - For each item with
"status":"MISSING"and a non-empty"fix", RUN that fix command yourself (the human approves via the permission prompt). Order: CORE (git/gh/python3) → CHECKER harness → COMPANIONS (herdr, ponytail, adhd;/loop-taskis bundled with this plugin). - For a MISSING item with an empty
"fix"(a companion whose source isn't wired in), tell the human the one concrete thing to provide (the marketplace or URL for that skill) and set the matchingSM_*env var — do not block the rest on it. - After healing, if the checker harness is present, confirm a reachable model with a dry check:
"${CLAUDE_PLUGIN_ROOT}/bin/reason.sh" --dry-run "ping"— and remind the human that cross-model checking needs a 2nd model family + credentials (SM_CHECKER_*/SM_REASON_*), which only they can supply. - Re-run
bash "${CLAUDE_PLUGIN_ROOT}/bin/doctor.sh"and report: what was already OK, what you fixed, what still needs the human.
Rule: propose and run the commands; the human's only job is to approve. Do not hand them a manual checklist.
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 · 22 lines · 47 tokens per session scan A b9104b747451
secondmate-doctor is a command published in the GitHub repository eshwarvijay/secondmate (3 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 392 once invoked, about $0.0002 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
insights
Surface patterns from your pro-workflow learnings and session history.
blackboard
Read or write a Network-AI blackboard key (shared multi-agent state).
cost-tracker
Track session costs, understand token spend, and get optimization tips.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
test
Agentic end-to-end test orchestrator — drive web/macOS flows, evaluate UX rubric, reconcile issues.
mach12:pr-merge
Merge a PR, delete the feature branch, and optionally create a release.