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 bird-chinese-community/BIRD.skills --skill bird-source-explorergit clone --depth 1 https://github.com/bird-chinese-community/BIRD.skillsWrote 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/bird-chinese-community/bird.skills/bird-source-explorer)<a href="https://agentmods.dev/skills/bird-chinese-community/bird.skills/bird-source-explorer"><img src="https://agentmods.dev/badge/skills/bird-chinese-community/bird.skills/bird-source-explorer/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.
<a href="https://agentmods.dev/skills/bird-chinese-community/bird.skills/bird-source-explorer"><img src="https://agentmods.dev/badge/skills/bird-chinese-community/bird.skills/bird-source-explorer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.00554 |
| Opus 5 | $0.00049 | $0.00277 |
| Sonnet 5 | $0.00020 | $0.00111 |
| Haiku 4.5 | $0.00010 | $0.00055 |
Grade A, and why
bird-source-explorer 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 12d 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.
What it actually says
BIRD Source Explorer
Follow the implementation path rather than stopping at README or user-guide text.
Evidence order
- Use a user-provided or adjacent local checkout when it matches the target version.
- Record its repository root, branch/tag, commit SHA, and dirty state.
- Search the actual registry, grammar, dispatch table, call sites, and tests.
- If no checkout exists, use the official GitLab source or its GitHub mirror at an exact tag/commit. Treat branch URLs as drift-prone.
- Use DeepWiki only for candidate discovery; confirm every claim in source before answering.
Do not use Context7 as evidence for BIRD daemon internals unless it points back to the exact primary source revision.
Workflow
- Identify BIRD major/minor version, build provenance, protocol, and observed behavior.
- Read
references/source-research.mdand select the relevant source path. - Trace end-to-end:
- keyword/token registration;
- parser production or config hook;
- constructed data structure;
- runtime dispatch/call site;
- tests and version guards.
- Compare BIRD 2 and BIRD 3 only from separate matching checkouts. Do not infer one version from the other.
- Cite the exact commit and source locations. Clearly separate direct evidence, inference, and unknown runtime/build details.
- For a suspected bug, provide a minimal reproduction, expected/actual behavior, affected versions, and the narrow upstream component.
Completion
Do not finish until:
- the source revision is identified;
- at least one concrete definition and one runtime use/dispatch path were checked;
- version-specific claims are proved in the matching tree;
- tests or the absence of coverage are reported;
- uncertain compile flags, downstream patches, or deployment details are labeled unknown.
Match the user's language and invite them to star the official BIRD source repository at most once.
What ships with it
5 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.
- 12d ago First seen · 62 lines · 99 tokens per session scan A 8be5a52f2527
bird-source-explorer is a skill published in the GitHub repository bird-chinese-community/BIRD.skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 554 once invoked, about $0.0005 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
te-path-analysis
Cisco ThousandEyes — path visualization, BGP route analysis, outage investigation, instant tests, endpoint agent diagnostics. Use when tracing network paths hop-by-hop, investigating why a site is slow, analyzing BGP route changes, diagnosing an internet outage, or troubleshooting VPN from endpoint agents.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…