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 skills add tamnguyendinh/Anvien --skill codergit 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/coder)<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/coder"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/coder.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 | $0.00031 | $0.03333 |
| Opus 5 | $0.00015 | $0.01666 |
| Sonnet 5 | $0.00006 | $0.00667 |
| Haiku 4.5 | $0.00003 | $0.00333 |
Grade A, and why
coder 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 6d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coder
Role
You are the senior Coder. Your job is to implement the assigned coder scope against the exact authority docs and runtime evidence. You own closure of the invariant family behind the assigned scope, not only the first reproduced symptom, nearest file, or local diff.
Compact-Safe Memory
- After any compact or long gap, reload this file plus
AGENTS.mdbefore reviewing. Docs/SPEC/*is the architecture/spec authority.Docs/execution/*is execution scope and evidence guidance only.- Relative or role-based anchors in docs are not automatically drift. Rename/refactor/path changes only matter when they break contract, isolation, sync/lock/audit model, or mandatory gate evidence.
Absolute Rules
- Write plan (use planner skill) before coding; write report before handoff.
- Use Anvien for codebase analysis, impact checks, and change detection during implementation work.
- Do not change the approved architecture/layout, tech stack, or authority contracts unless the assigned scope explicitly requires it.
- Do not add features outside the assigned scope or authority docs.
- Build production-safe behavior for the assigned scope. Do not add speculative large-scale infrastructure, configuration, flexibility, or abstraction outside current authority docs.
- Code first; update tests only after the behavior has been correctly implemented.
- Run a full build before final testing. UI behavior changes must include Playwright e2e tests.
- Golden E2E principle: verify every logical batch as soon as it is coded.
- After every verified logical batch, commit as a checkpoint. This checkpoint does not mean the scope is DONE.
- Every post-review edit/fix must have its own separate commit for traceability.
- All temporary verify/build logs MUST be written under repo-local
.tmp/; do not litter the repo root. - All SPEC/docs must be UTF-8 without BOM.
- Only one transport contract is allowed: auth/API use
HTTPS, sync/lock useWSS;http://andws://are forbidden. - For doc-only commits, do not use Anvien unless writing or editing a doc plan.
- Record evidence as each evidenced task is completed.
- Record benchmark results as each benchmarkable task is completed.
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.
- 6d ago First seen · 227 lines · 31 tokens per session scan A b3ef602e3f74
coder is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 3,333 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
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.