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/manusco/resonance/observabilitynpx skills add manusco/resonance --skill observabilitygit clone --depth 1 https://github.com/manusco/resonanceWrote 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/manusco/resonance/observability)<a href="https://agentmods.dev/skills/manusco/resonance/observability"><img src="https://agentmods.dev/badge/skills/manusco/resonance/observability.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02003 |
| Opus 5 | $0.00000 | $0.01001 |
| Sonnet 5 | $0.00000 | $0.00401 |
| Haiku 4.5 | $0.00000 | $0.00200 |
Grade A, and why
resonance-ops-observability 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 4d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-ops-observability: instrument the running system, not the build
Expertise: telemetry for live systems: logs, metrics, traces, SLOs, and alerts that page a human only when a human is needed. Apply when: a system is running in production (or about to be) and you need to know what it is doing, why it broke, or whether it is meeting its promise to users.
You make a system explainable while it runs. Monitoring answers questions you already knew to ask (a fixed dashboard, a threshold you set). Observability lets you ask new questions of a live system without shipping new code, because the telemetry was rich enough to slice after the fact. Design for the unknown-unknown: the incident nobody predicted.
This is distinct from two neighbors. resonance-ops-qa tests the system before release (does the code work). resonance-ops-system-health scores the codebase as an artifact (is the repo healthy). You own the third axis: the system is already live and serving real traffic. Different question, different tools.
How this expert thinks
Instrument for the question you cannot yet ask. You will not predict the next outage. So the goal is not "log everything" (that buries signal and costs a fortune); it is high-cardinality, structured, correlatable telemetry that lets you decompose a problem after it appears. Wide structured events beat many narrow log lines. When in doubt, add a dimension (user_id, region, version), not another log statement.
Symptom, not cause, is what pages a human. Alert on what the user feels: latency, errors, unavailability. Do not alert on causes (CPU is 90%, a pod restarted) unless that cause is itself an unrecoverable symptom. A system can run hot and serve every request fine. Paging on the cause trains people to ignore pages, and an ignored pager is worse than no pager.
An alert without an action is noise. Every alert that reaches a person must map to a decision they can make right now. If the runbook is "watch it," it is a dashboard, not an alert. Noise is not free: it burns the on-call's trust and attention, and trust is the thing you need intact at 3am during the real incident.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/01_golden_signals_instrumentation.json 974 B
- evals/02_slo_error_budget_design.json 1.1 KB
- evals/03_alert_noise_and_vanity_dashboards.json 1.2 KB
- evals/04_planted_defect.json 1.2 KB
- references/alerting_design.md 8.1 KB
- references/observability_pillars.md 9.3 KB
- references/slo_error_budgets.md 6.6 KB
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.
- 4d ago First seen · 77 lines · 0 tokens per session scan A 9addec2eb917
resonance-ops-observability is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,003 tokens. 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
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
memstack-business-scope-of-work
Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
copy-trading
Wallet evaluation, monitoring, and copy-trade strategy design for Solana DEX trading.