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-debuggingnpx skills add evoelsewhere/evoflux --skill coding-debugginggit clone --depth 1 https://github.com/evoelsewhere/evofluxWhat 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 | $0.00071 | $0.01005 |
| Opus 5 | $0.00036 | $0.00502 |
| Sonnet 5 | $0.00014 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
coding-debugging 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug a code failure
Treat debugging as a causal investigation. A passing build after an edit is not proof unless the edit explains the original symptom. Do not load bundled references when this skill activates.
Establish the failure contract
Record the exact input, environment, expected result, observed result, and earliest known failing boundary. Preserve the original error, stack, status, timing, or corrupted value. Distinguish a product failure from an incorrect test expectation or environment mismatch.
Reproduce and narrow
- Reproduce with the smallest deterministic command or interaction that still fails. If reproduction is blocked, identify the missing state or evidence.
- Compare one dimension at a time: input, configuration, version, process, timing, identity, or dependency.
- Trace backward from the first bad observation through state transitions and exact symbol relationships. Use literal discovery for errors, configuration, generated values, and registration keys.
- Form one falsifiable hypothesis. Run the cheapest check that could disprove it before editing production code.
- Keep a short hypothesis ledger when more than two plausible causes survive. Read references/hypothesis-led-debugging.md for the ledger format, failure classes, and causal-proof standard.
Navigate structural evidence
When the failure location or exact identifier is unknown, call code_context with action="search"
once with the literal error, configuration key, runtime term, or code fragment.
Use its repository-qualified source range to identify a declared symbol. If the
exact symbol is already visible, skip code_context with action="search"; it is discovery, not
structural proof.
Once source evidence reveals an exact function, method, class, or qualified
symbol, use code_context to test the relevant structural hypothesis:
callers for inbound paths, callees for downstream calls, references for
non-call uses, or neighborhood for the immediate boundary. Start at depth 1.
Static edges narrow the causal path but do not prove runtime order, state, or a
race; preserve the reproduction as the final causal test.
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.
- yesterday First seen · 98 lines · 71 tokens per session scan A 1dc03b336e93
coding-debugging is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,005 once invoked, about $0.0004 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
kane-cli
Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…
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.
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…