A coding assistant for BIRD, an open-source routing daemon that exchanges network routes, using the @birdcc toolchain.

Use it to discover, lint, format, parse, and validate BIRD configuration files, filters, protocols, and include relationships.

It helps identify real BIRD projects, catch configuration errors, and inspect changes without accidentally starting or reloading a live routing service.

bird-agent — Skill for Claude Code and Codex by bird-chinese-community

Install

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.

Any agent

npx skills add bird-chinese-community/BIRD.skills --skill bird-agent

Clone the repo

git clone --depth 1 https://github.com/bird-chinese-community/BIRD.skills

Made for: Claude Code, Codex.

Or install bird-agent, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bird-chinese-community/bird.skills/bird-agent/github.svg)](https://agentmods.dev/skills/bird-chinese-community/bird.skills/bird-agent)

Your own site

<a href="https://agentmods.dev/skills/bird-chinese-community/bird.skills/bird-agent"><img src="https://agentmods.dev/badge/skills/bird-chinese-community/bird.skills/bird-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bird-chinese-community/bird.skills/bird-agent"><img src="https://agentmods.dev/badge/skills/bird-chinese-community/bird.skills/bird-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,334 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00151	$0.01334
Opus 5.5	$0.00060	$0.00534
Sonnet 5.5	$0.00030	$0.00267
Haiku 4.5	$0.00015	$0.00133

Measured 2mo ago against content hash 159c03672505, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bird-agent 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/detect_bird_context.py, scripts/run_birdcc.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

bird-agent/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BIRD Config Agent

Use the current @birdcc/cli project model instead of treating every .conf file as BIRD. Prefer parser-backed diagnostics and read-only discovery before changing a configuration.

Safety invariants

Do not publish or commit unredacted BGP passwords, peer addresses, ASNs, communities, or private route-policy details. Read references/safety.md before handling production material.
Do not write config files by default. Run formatting in check mode first. Pass --write --confirmed to the wrapper only after the user explicitly authorizes the edit.
Treat birdcc init --write and --force as writes. Start with birdcc init . --dry-run --json.
Use bird -p -c <file> for a read-only daemon parse check; do not start or reload BIRD unless the user explicitly requests the operational change.
Do not infer that a generic .conf file is BIRD from its extension alone. Require a canonical name, an explicit project config, or parsed BIRD declarations.

Workflow

Run uv run scripts/detect_bird_context.py --root . from the skill directory. Inspect project_config, candidate files, installed tool versions, and the read-only birdcc_project_detection report.
Read references/project-config.md when discovery is ambiguous, the repository has multiple routers, or no project config exists. Prefer bird.config.json; accept birdcc.config.json only as a compatibility alias.
Run diagnostics through the safe wrapper:
```
uv run scripts/run_birdcc.py lint <entry-file> --root .
```
Add --bird when the matching BIRD binary is available. Cross-file include analysis is enabled by the current CLI unless the project configuration disables it.
Report every diagnostic with source path, line/column, code, severity, and a concrete fix. The current JSON result is an object containing diagnostics, not a bare diagnostics array.
For formatting, preview first:

Read the full file on GitHub · 116 lines

Files

What ships with it

20 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.

Changes

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.

2mo ago First seen · 116 lines · 151 tokens per session scan A 159c03672505

Subscribe to this mod's changes

bird-agent is a skill published in the GitHub repository bird-chinese-community/BIRD.skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 151 tokens to every session and 1,334 once invoked, about $0.0006 per session on Opus 5.5. 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.

DevOps and cloud agent-skills bgp bgp-configuration bird bird-internet-routing-daemon bird2

bird-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bird-agentbird-chinese-community/BIRD.skills	Skill	7	3mo ago	MIT	A	151	Claude Code, Codex
bgp-registry-intelautomateyournetwork/netclaw	Skill	722	yesterday	Apache-2.0	A	97	Claude Code
te-path-analysisautomateyournetwork/netclaw	Skill	722	yesterday	Apache-2.0	A	100	Claude Code, Codex
email-auditmessagebird/bird-ai	Skill	9	yesterday	MIT	A	40	Claude Code
bird-climessagebird/bird-ai	Skill	9	yesterday	MIT	A	40	Claude Code
amb-receive-replymessagebird/bird-ai	Skill	9	yesterday	MIT	A	28	Claude Code, Codex
email-receive-replymessagebird/bird-ai	Skill	9	yesterday	MIT	A	28	Claude Code, Codex