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 skills/boshu2/agentops/rchnpx skills add boshu2/agentops --skill rchgit clone --depth 1 https://github.com/boshu2/agentopsWhat 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 | $0.00032 | $0.00840 |
| Opus 5 | $0.00016 | $0.00420 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
rch 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RCH — remote compilation specialist
RCH can offload one explicit compilation command or inspect the remote compiler path. This skill reports what happened; it does not govern retries or repair.
Staged diagnosis works because the offload pipeline fails in order — availability, configuration, hook, classification, sync, remote compile, worker pressure — so the first failing stage localizes the fault and every later stage is noise until it passes. Remediate in irreversibility order: read-only probes and config inspection before daemon restarts, restarts before cleanup, and destructive cleanup or worker mutation only with explicit caller authority.
Named failure mode — green-local blindness: a passing [RCH] local (...)
build read as offload success; the local fallback hid that the remote claim
was never proved.
Anti-pattern: re-running the build hoping the fallback reason disappears. Corrective: read the recorded fallback reason and fix that stage; the pipeline fails deterministically, not moodily.
Procedure
- Capture
rch check,rch doctor --json, worker status, and the relevant[RCH]summary before mutation. - For diagnosis, identify the first failing stage: availability, configuration, hook, classification, sync, remote compile, or worker pressure.
- Run only the caller-authorized command or documented safe diagnostic once.
- Capture the exact command, worker when known, exit code, local-fallback reason, and post-action status.
- Stop and return the evidence.
[RCH] local (...) means the requested remote-offload claim was not proved even
when the local build succeeds. Destructive cleanup, worker deployment, daemon
configuration, and remote mutation require explicit caller authority.
rch check exit status adjudicates readiness (0 = ready, nonzero = not
offload-ready). Do not read rch doctor --json success: true as readiness — a
successful diagnostic report can coexist with a down daemon or unreachable
workers. Adjudicate on rch check; use doctor for the reasons behind it.
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.
- 3d ago First seen · 87 lines · 32 tokens per session scan A 5b1953444bca
rch is a skill published in the GitHub repository boshu2/agentops (431 stars, last pushed 5d ago), licensed Apache-2.0. It adds 32 tokens to every session and 840 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 2026-08-30.
Other skills, from other repositories
brainstorm
Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or…
doc-review
Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
doubt-driven
Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.
drift-detect
Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project. For doc-vs-code drift inside a specific diff, use sync-docs.