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/m-binimran/dev-pack/observabilitynpx skills add m-binimran/dev-pack --skill observabilitygit clone --depth 1 https://github.com/m-binimran/dev-packWhat 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 | $0.00046 | $0.00381 |
| Opus 5 | $0.00023 | $0.00191 |
| Sonnet 5 | $0.00009 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
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 yesterday.
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.
What it actually says
observability
You can't fix what you can't see. Capture errors with context; don't capture secrets.
Error monitoring
- Sentry (or equivalent) on client, server, and edge. Source maps uploaded so stack traces are readable.
- Capture in
error.tsxboundaries and in route handler/action catch blocks — re-throw or report, don't swallow. - Attach context: route, user id (not email/PII), request id. Scrub tokens, passwords, card data, full emails.
Logging
- Structured (JSON) logs with a level (
info/warn/error) and a request/correlation id, not bareconsole.logstrings. Log decisions and failures, not noise. - Log server-side only; never log secrets, full request bodies with credentials, or PII.
- One line per meaningful event; include enough to reproduce, nothing more.
What to watch
- Error rate + new error types after a deploy, slow routes/queries (pair with
query-optimizer), failed webhooks/payments, auth failures spiking.
Output
- The Sentry init (client/server/edge), the logging helper, and the PII-scrubbing rules applied.
Guardrails
- Monitoring must not become a leak: no secrets/PII in events or logs (the
secret-scanhook guards code, but you must scrub runtime values too). - Don't ship
console.logdebugging to production (thecode-qualityrule forbids it) — use the logger.
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.
- yesterday First seen · 32 lines · 46 tokens per session scan A 4603e5395fab
observability is a skill published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 381 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 2026-08-31.
Other skills, from other repositories
investigate-issue
Investigate a GitHub issue by fetching details, analyzing the codebase, researching documentation, and presenting an actionable implementation plan with test guidance. Use when asked to investigate, analyze, triage, or plan work for a GitHub issue. Invoked with /investigate-issue or /investigate-issue (prompts for ID).
resolve-pr-comments-stack
Resolve unresolved PR review comments across an entire Graphite (gt) stack of many PRs, bottom-up, in one working directory. Use when asked to "go through this stack and resolve comments", "clean up review comments across the whole stack", or given a list/range of PR numbers that form (or partially form) a gt stack.…
resolve-pr-comments
Skill "resolve-pr-comments" from maximhq/bifrost, covering resolve pr comments, usage, workflow overview, step 1: detect repository and step 2: fetch unresolved comments (graphql).
harness-test-writer
Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…
trulens-blocking-guardrails
Configure and use feedback functions as runtime blocking guardrails.
review-pr
Reviews a PR or diff with multi-angle finders and adversarial verification, then reports a findings table, a merge/no-merge recommendation, required followups, and offers to create a follow-up PR. Use when the user types /review-pr [PR# | branch | path].