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 skills add terva-sh/terva --skill troubleshoot-tervagit clone --depth 1 https://github.com/terva-sh/tervaWrote 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/skills/terva-sh/terva/troubleshoot-terva)<a href="https://agentmods.dev/skills/terva-sh/terva/troubleshoot-terva"><img src="https://agentmods.dev/badge/skills/terva-sh/terva/troubleshoot-terva/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/skills/terva-sh/terva/troubleshoot-terva"><img src="https://agentmods.dev/badge/skills/terva-sh/terva/troubleshoot-terva.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 | $0.00083 | $0.01022 |
| Opus 5 | $0.00042 | $0.00511 |
| Sonnet 5 | $0.00017 | $0.00204 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
troubleshoot-terva 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting terva
Work symptom-first, and mind one boundary throughout: some diagnostic
surfaces are yours to read, others are deliberately denied to tools —
credentials, transcripts, and most of $TERVA_HOME/logs/. When a step below
says "ask the user", that denial is why; ask for the command's output instead
of trying to route around it.
First moves for any symptom: terva_status (who/where/model/session), and
the relevant picker — /skills, /extensions, /mcp, /sessions.
Extension won't load or its tools are missing
terva ext list— is it discovered at all? The install-dir basename and the manifest are different names;ext listshows both.- Not listed: project-local extensions load only in a trusted workspace
(
terva trust); global ones ($TERVA_HOME/extensions/) always load. Checkenabledin its manifest and the user'sdisable_extensionslist. - Listed but dead: read its log —
$TERVA_HOME/logs/ext-<name>.logis readable by your tools (the one carve-out from the logs denial), orterva ext logs <name> [-f]. Build failures from its launcher land there. - Empty log + "off (not running)" is the classic launcher trap: the
manifest's
execisn't executable (a plain file-write drops the exec bit), so it dies on EACCES before writing a byte. - Tools present earlier but gone now: check the run's scoping flags
(
--extensions,--mcp,--toolsrestrict per run) and the approval mode — plan-style modes withhold mutating tools on purpose.
Bot / connector down
Connector logs (logs/connector-<name>.log) are not readable by your
tools — ask the user for terva bot status output and the log tail.
Useful structure for the ask: the connector's status/configured verbs
report credential state; repeated crash-restarts exhaust a 3-per-60s budget
and the bridge reports broken; a connect_error means bad credentials
(re-run setup), while transient network trouble self-retries and only warns.
Pairing and group admission are host-side: a silent bot in a group chat is
usually unapproved (owner /approve in-chat), not broken.
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.
- 12d ago First seen · 80 lines · 83 tokens per session scan A 457f57c799fc
troubleshoot-terva is a skill published in the GitHub repository terva-sh/terva (2 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 1,022 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 skills, from other repositories
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
pi-sync
Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.
javascriptcore-garbage-collector
JSC GC reference for Bun. Use for use-after-free, JS object leaks, "collected too early", or when touching WriteBarrier, visitChildren, visitAdditionalChildren, JSRef, JSC::Strong/Weak, hasPendingActivity, ensureStillAlive, addOpaqueRoot, reportExtraMemoryAllocated, IsoSubspace, HeapAnalyzer, finalize.
pi-go-review
Review ported Go code for idiomatic quality — that the port maximizes Go rather than transliterating TypeScript. Use after porting upstream pi changes, or standalone on any diff in this repo.
ci-self-heal
A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.