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/techymt/claude-code-superpowers/observabilitynpx skills add TechyMT/claude-code-superpowers --skill observabilitygit clone --depth 1 https://github.com/TechyMT/claude-code-superpowersWhat 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 | $0.00097 | $0.02071 |
| Opus 5 | $0.00048 | $0.01035 |
| Sonnet 5 | $0.00019 | $0.00414 |
| Haiku 4.5 | $0.00010 | $0.00207 |
Grade A, and why
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 2d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability
The pattern
Claude Code has a strict separation between diagnostic logs (structured, PII-safe, written to log files) and tool result content (what the LLM and user see). For local debug output, use logForDebugging(message, data?) from src/utils/debug.ts. For analytics telemetry events sent to Anthropic (with user consent), use logEvent('event_name', metadata) from src/services/analytics/index.ts. Tool results are returned as strings in ToolResult.data or ToolResult.error.
The PII-safety contract is enforced at the type level: analytics metadata must be typed as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS — the suffix is a code-review reminder that the values you are passing are not file contents, user input, or anything identifying.
Startup performance is tracked with profileCheckpoint(label) — a lightweight timer that records the time since the previous checkpoint. Token usage is tracked in cost-tracker.ts, which accumulates input/output tokens across turns and provides totals for the UI's cost display.
Why this matters
Claude Code runs on user machines and sends analytics data to Anthropic (with user consent). The _I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS suffix on the metadata type is a reminder enforced by code review: log operation types, timings, and error types — but never file contents, user input, command arguments, or anything that could identify the user or their work.
Startup profiling exists because startup latency is user-visible. A regression in imports_loaded timing (before any user code runs) tells engineers which module import caused the slowdown without needing to reproduce locally.
Token cost tracking is a user feature (the session cost display) and an internal constraint (auto-compaction triggers when context approaches the limit). Both consumers use the same accumulator.
How to apply it
- Track operation start/end times with
logEvent('operation_completed', { duration_ms } as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS). Include a duration measurement. - Log error types (not error messages) — error messages often contain user data.
- Use event names as snake_case strings:
'git_status_started','tool_call_failed','mcp_reconnected'. - Use
logForDebugging('message', { context })for local-only debug output that should not go to telemetry. - Add
profileCheckpoint('label')at natural initialization boundaries. - Track token usage via
cost-tracker.ts— don't implement a second accumulator. - Never include in telemetry: file contents, user input, command arguments, file paths, API responses, or any string that might contain user data.
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.
- 2d ago First seen · 183 lines · 97 tokens per session scan A a274a38ca552
observability is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 2,071 once invoked, about $0.0005 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
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
pedagogy-review
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…