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/debugnpx skills add evoelsewhere/evoflux --skill debuggit 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 | $0.00020 | $0.00463 |
| Opus 5 | $0.00010 | $0.00231 |
| Sonnet 5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
oad/debug 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
Debug the reported issue.
Workflow:
-
Triage the report
- Extract the symptom, expected behavior, reproduction steps, affected surface (backend/frontend/desktop/agent/provider), session id, workspace, model, logs, and timing clues.
- If the report is ambiguous, inspect available evidence first; ask only when a missing decision blocks safe progress.
-
Choose the fastest evidence path
- Live session / agent behavior: use the API endpoints directly or the test suite:
uv run pytest tests/agent/mode/team/ -q - Backend/API issue: hit the smallest route/service path, inspect logs, then add/adjust pytest coverage.
- Frontend issue: inspect relevant components/hooks/stores, run focused
bunchecks/tests, and use existing UI state patterns. - Desktop/CLI/provider issue: inspect the specific command/provider path and environment assumptions.
- Live session / agent behavior: use the API endpoints directly or the test suite:
-
Reproduce narrowly
- Recreate the smallest scenario that demonstrates the bug.
- Match the user's mode/workspace/model/message sequence when relevant.
- Capture durable evidence: raw HTTP response, persisted history, SSE events, logs, failing test output, or UI state.
-
Diagnose from code and evidence
- Search for existing patterns before editing.
- Identify the boundary that failed: route validation, persistence, queueing, stream emission, agent loop, hook, tool, provider, frontend store, or renderer.
- Preserve unrelated work; do not reset or overwrite changes you did not make.
-
Fix surgically
- Make the smallest change that addresses the proven root cause.
- Add or update focused regression coverage at the closest layer.
- Update related docs only when behavior, API contract, or operator workflow changed.
-
Verify and report
- Re-run the reproduction and the focused tests/checks for touched areas.
- If feasible, run the repository's standard lint/type/test commands for the changed surface.
- Report root cause, changed files, checks run with results, and any remaining risk or unverified area.
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 · 42 lines · 20 tokens per session scan A ce6ca6365b72
oad/debug is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 20 tokens to every session and 463 once invoked, about $0.0001 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…