Borrowing it
Nothing to install: this file belongs to liatrio/liatrio-otel-collector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/liatrio/liatrio-otel-collector/main/.claude/skills/renovate-semconv/SKILL.mdgit clone --depth 1 https://github.com/liatrio/liatrio-otel-collectorWrote 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/liatrio/liatrio-otel-collector/renovate-semconv)<a href="https://agentmods.dev/skills/liatrio/liatrio-otel-collector/renovate-semconv"><img src="https://agentmods.dev/badge/skills/liatrio/liatrio-otel-collector/renovate-semconv/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/liatrio/liatrio-otel-collector/renovate-semconv"><img src="https://agentmods.dev/badge/skills/liatrio/liatrio-otel-collector/renovate-semconv.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 | $0.00175 | $0.01016 |
| Opus 5.5 | $0.00070 | $0.00406 |
| Sonnet 5.5 | $0.00035 | $0.00203 |
| Haiku 4.5 | $0.00017 | $0.00102 |
Grade A, and why
renovate-semconv 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 22d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playbook: semantic conventions (semconv)
Semconv is not a Renovate group — Renovate deliberately does not bump the semconv package (it is
a manual migration). This playbook is therefore selected by failure signature during a /fix
run, not by a group label: a collector-core bump (renovate-otel-core)
can surface semconv breakage in generated code, and the compiler errors then match the failure
signatures in this skill's description. A direct go.opentelemetry.io/otel/semconv/** reference is
a secondary hook for the rare case Renovate touches the package.
This is a judgment-tier class, not a mechanical one. A semconv migration is best-effort at most; do not report it as a completed fix. See spec Unit 3 for the three-tier classification.
Authoritative docs
docs/semantic-conventions.md— the full policy: spec-vs-package version axes, the version matrix, the extensions register, and the package upgrade / OCB / Renovate runbook.docs/semantic-conventions.md→ Rule of thumb — default to the spec at the version our packages declare, not whatever is newest upstream.AGENTS.md→ Semantic conventions — the short-form posture and the "do not bump the semconv package as a side effect" guardrail.
Failure modes → remediation
| Failure signature | Likely cause | Remediation |
|---|---|---|
undefined: semconv.<Const> after a core bump |
an attribute/const was renamed or removed between semconv package versions | look up the new name in the declared spec version; update the reference to the spec name (an extension attribute is replaced by the spec name when the spec defines one) |
sem_conv_version mismatch in metadata.yaml vs imported package |
the declared spec version and the Go package version diverged | reconcile per the version matrix; do not silently bump the package to satisfy the code |
| generated code references a semconv version the package does not export | mdatagen tried to stamp an import that does not exist (package lags the spec) | the package version is the hard ceiling — stay at or below it; this is why the bump may only be best-effort |
| behavioral / attribute-meaning change | a spec revision changed semantics, not just names | defer — this is not mechanical; record it in the recap's "What's left" |
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.
- 22d ago First seen · 57 lines · 175 tokens per session scan A e8cd083753f0
renovate-semconv is a skill published in the GitHub repository liatrio/liatrio-otel-collector (47 stars, last pushed today), licensed Apache-2.0. It adds 175 tokens to every session and 1,016 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-15.
renovate-semconv compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| renovate-semconvliatrio/liatrio-otel-collector | Skill | 47 | today | Apache-2.0 | A | 175 | Claude Code |
| backstage-techdocsbendaamerahmed/backstage-idp-plugin | Skill | 1 | 2mo ago | MIT | A | 51 | Claude Code |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | 11d ago | MIT | A | 69 | Claude Code |
| atmos-profilescloudposse/atmos | Skill | 1.4k | yesterday | Apache-2.0 | A | 35 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.1k | yesterday | MIT | A | 56 | Claude Code, Codex |
| monorepo-managementwshobson/agents | Skill | 42k | yesterday | MIT | C | 54 | Claude Code |
| managing-github-actions-secretsPostHog/posthog-foss | Skill | 728 | yesterday | MIT | A | 67 | Claude Code, Codex |