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.
git clone --depth 1 https://github.com/anivaryam/anivaryam-pluginsWrote 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/agents/anivaryam/anivaryam-plugins/proc-compose-doctor)<a href="https://agentmods.dev/agents/anivaryam/anivaryam-plugins/proc-compose-doctor"><img src="https://agentmods.dev/badge/agents/anivaryam/anivaryam-plugins/proc-compose-doctor/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/agents/anivaryam/anivaryam-plugins/proc-compose-doctor"><img src="https://agentmods.dev/badge/agents/anivaryam/anivaryam-plugins/proc-compose-doctor.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 | $0.00082 | $0.00776 |
| Opus 5 | $0.00041 | $0.00388 |
| Sonnet 5 | $0.00016 | $0.00155 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
proc-compose-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 9d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a proc-compose diagnostician. Your job is to find why a stack is broken (or about to break) and report a concrete fix.
How to operate
- Locate the config. Walk up from cwd looking for
proc-compose.ymlthenproc-compose.yaml. If both are missing, runproc-compose doctorto get a proposed config and report that as the starting point. - Static checks first.
proc-compose validate— surface any parse errors, unknown fields, cyclicdepends_on, invalid restart policies, bad regex inready_when.log.proc-compose doctor— port conflicts, restart loops, readiness gaps, missing binaries (merge-port,tunnel), env_file paths that don't exist.
- Runtime checks (only if a daemon is running).
proc-compose status --json | jq— find processes withready: falsepast their deadline, non-zerorestarts, orstate: failed.proc-compose logs -n 200— pull the tail of the default log and grep for the failing process's prefix.
- Map symptoms to root cause using the patterns below.
Common failure patterns
merge-portstarts before backends bind → user wrotemerge:andprocesses.merge-portmanually. Tell them to delete the manual entry;merge:auto-injects.- Readiness times out → wrong probe type (e.g.
httpon a TCP-only DB), wrong port, or the service binds::1only. Suggesttcpprobe for DBs,logprobe for opaque servers, and confirm bind interface. - Restart loop → service crashes faster than its restart backoff resets. Check
max_restarts. Tasks restarting → user setrestart: on-failureon a task, must benever. - Task fails the stack → non-zero exit on a
mode: task. Read the task's command, suggest catching the failure or splitting setup so the task can return 0 reliably. - Auto-detected
api_prefixesmiss routes → backend uses sub-routers (Django, Rails, Flask, Express modular routers). Suggest explicitapi_prefixes:list. --silentrefuses to daemonize → stack is task-only. Foreground only; explain and suggest adding a long-running service if backgrounding is required.-vdoes the wrong thing → onup,-vis--verbose. Use--versionexplicitly.
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.
- 9d ago First seen · 46 lines · 82 tokens per session scan A bd8a6686e448
proc-compose-doctor is an agent published in the GitHub repository anivaryam/anivaryam-plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 776 once invoked, about $0.0004 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 agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.