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/tamnguyendinh/anvien/debuggingnpx skills add tamnguyendinh/Anvien --skill debugginggit clone --depth 1 https://github.com/tamnguyendinh/AnvienWrote 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/tamnguyendinh/anvien/debugging)<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/debugging"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/debugging.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 5.1 | $0.00011 | $0.01658 |
| Opus 5 | $0.00005 | $0.00829 |
| Sonnet 5 | $0.00002 | $0.00332 |
| Haiku 4.5 | $0.00001 | $0.00166 |
Grade A, and why
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 5d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging With Anvien
Use this skill to debug from symptom to verified fix in repositories where Anvien rules or Anvien evidence apply. The workflow is continuous: capture the failure, reproduce it, locate the owner, trace the root cause, write a plan, check impact, fix the source, add defenses when needed, and verify with fresh evidence.
Iron Laws
- MUST understand the root cause before fixing.
- MUST write a plan before fixing.
- MUST run a full build before testing when active repository rules require it.
- MUST verify with fresh evidence before claiming completion.
- MUST follow active repository rules, including Anvien rules when present.
Phase 1: Capture The Symptom
Record the failing command, log, stack trace, screenshot, test, route, input, output, or runtime behavior.
Do not propose a fix yet.
Phase 2: Reproduce
Reproduce the failure consistently.
If the failure is not reproducible, gather more evidence instead of guessing:
- run the failing command again
- isolate the input
- capture logs
- add temporary diagnostic instrumentation when appropriate
- compare local, CI, browser, runtime, and environment differences
Phase 3: Locate Candidate Owner
Use source inspection, logs, tests, and repository tools to identify the likely owner.
When active repository rules require Anvien:
- Run
anvien analyze --forcebefore graph-based investigation. - Unknown owner:
anvien query "<symptom>" --repo <repo> - Candidate files:
anvien query files "<symptom>" --repo <repo> - Suspect file:
anvien file-detail <path> --repo <repo> --json - Suspect symbol:
anvien context symbol "<symbol>" --repo <repo> - Ambiguous symbol:
anvien context symbol "<symbol>" --file <path> --repo <repo> - Route, tool, consumer, or contract behavior:
anvien query api,anvien api route-map,anvien api tool-map,anvien api shape-check, oranvien api impact - Graph, index, resolution, source-site, or retrieval quality issue:
anvien graph-health summary --repo <repo> --json,anvien graph-health files --repo <repo> --json,anvien graph-health explain "File:<path>" --repo <repo> --json,anvien resolution-inventory --graph .anvien/graph.json,anvien source-site-accuracy --graph .anvien/graph.json, oranvien query-health --repo <repo> - Stuck analyze, stale MCP server, lock, or runtime process issue:
anvien doctor locks --repo <repo> --jsonoranvien doctor processes --json
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.
- 5d ago First seen · 173 lines · 11 tokens per session scan A 9d3abaa21bb0
debugging is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 1,658 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
swarm-orchestrate
Optional autonomy control plane — configure, plan, launch, monitor, recover, or stop local CLI-agent workers through SwarmVault's durable supervisor. Use for fit/budget-aware platform + model + reasoning-effort routing; a consistent pre-start/live/boundary/on-demand board with ticket drill-down; TOLD/MEASURED/EST…
swarm-design-deep
The developer-driven design lane — the user commits to each approach before anything is written, then the design goes to pseudocode, algorithms, invariants, sequence diagrams and test vectors in their chosen design language. Use when the user wants to own the system rather than receive it: "developer mode"…
swarm-flow
The SDLC router — figures out where a project stands and runs the right phase. Use at the START of any work in a SwarmVault project: continuing/resuming a project, starting a new one, "what's next", or before writing any feature code, spec, design, or ticket. Also use when unsure which phase (requirements, design…
swarm-design-ui
UI/UX design phase — propose an intentional design system (pattern, brand, color, typography, spacing, atomic components) with the user, offering distinct directions and per-page layout options, for any interface type: Web, Mobile, Desktop, TUI, or CLI. Use when the SRS declares a user interface, when defining a…
swarm-vault
The vault contract — how any agent reads, writes, and queries the SwarmVault. Use at the start of work in any vault-connected project, before exploring the repo, when deciding where to record memory/plans/decisions/sessions, when handing off between sessions or agents, or whenever unsure how the vault works.
swarm-init
Start a new project connected to the SwarmVault — register it, wire platform adapters, offer git init, set vault-as-default. Use when starting a new project, connecting a project to the vault, or when the user asks to set up SwarmVault in a directory.