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/evoelsewhere/evoflux/coding-observabilitynpx skills add evoelsewhere/evoflux --skill coding-observabilitygit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/coding-observability)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/coding-observability"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/coding-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 | $0.00091 | $0.00911 |
| Opus 5 | $0.00046 | $0.00456 |
| Sonnet 5 | $0.00018 | $0.00182 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
coding-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 today.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instrument code for observability
Telemetry without a question behind it is noise, not signal: name what an operator would need to know before adding a log, metric, trace, or alert. Do not load bundled references when this skill activates.
Name the question first
- State two to four concrete on-call or debugging questions this telemetry must answer (e.g. "is this queue backing up," "which tenant is causing the error spike"). Reject an instrumentation request with no question behind it; ask what it is meant to diagnose.
- Choose the signal that answers each question: logs for what happened at a point in time, metrics for how often/how fast in aggregate, traces for where time went across a call chain. Do not default to logging everything.
- Read references/signal-selection.md for RED/USE selection, correlation-ID placement, cardinality limits, and alert design.
When the owning boundary for a signal is not yet an exact symbol, call
code_context with action="search" once using the operation or error
text. Skip search when the exact symbol is already known.
For an exact symbol being instrumented, use code_context to confirm its
direct callers (who triggers it) and callees (what it depends on) so the
correlation ID or span is attached at the actual request boundary, not an
internal helper. Start at depth 1. Once the boundary is known, make the graph
the next structural observation instead of continuing broad discovery.
Keep refresh=true for the first indexed query and after edits. Use
refresh=false only for an immediate follow-up that intentionally reuses the
same index version.
Read references/code-context-contract.md only after a result exposes ambiguity, cross-repository scope, or another static fallback gap.
Instrument
Use stable, named event identifiers rather than interpolated free-text messages so logs stay queryable as the message wording changes. Generate a correlation ID at the boundary that owns the request and propagate it through every downstream call and log line. Never attach a high-cardinality value — user ID, raw URL, request ID — as a metric label; put it in a log or trace instead, and keep metric labels bounded to a known, small set of values.
What ships with it
4 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.
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.
- today First seen · 83 lines · 91 tokens per session scan A ec5c95986f18
coding-observability is a skill published in the GitHub repository evoelsewhere/evoflux (7 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 911 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 2026-09-05.
Other skills, from other repositories
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.
E2E Testing Nori Skillsets Subcommands
Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation.
general-video
The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a…
release
Autonomously cut a Rove (@sma1lboy/rove) release end-to-end — detect the semver bump from pending changesets (flagging an upstream minor you didn't intend), run the release gates, bump/tag/push via scripts/release.sh, then poll the GitHub Actions Release workflow with gh until npm publish completes, diagnosing CI…
hyperframes-cli
HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, or remove-background, or when troubleshooting the…
changelog-generator
Draft Rove release notes as Changesets. Writes user-facing entries as .changeset/.md files for @sma1lboy/rove (consumed into packages/kobe/CHANGELOG.md at release time). Use when the user asks for "changelog", "release notes", "what changed", "add a changeset", or before cutting a version. Enforces Rove's no-soft-wrap…