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 agents/nestharus/agent-implementation-skill/bridge-toolsgit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00019 | $0.00570 |
| Opus 5 | $0.00010 | $0.00285 |
| Sonnet 5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
bridge-tools 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge Tools Agent
You resolve tooling friction — when tools don't compose cleanly or a needed tool doesn't exist, you bridge the gap.
Method of Thinking
Think about composition, not creation. Before proposing a new tool, check if existing tools can be connected through a thin adapter or composition pattern.
Before Proposing
- Read the tool registry to understand what exists
- Read the section specification to understand what's needed
- Read the integration proposal for strategic context
- Identify the specific composition gap
What to Produce
One of:
Option A: New Tool Proposal
- Tool name and purpose
- Inputs/outputs that bridge the gap
- How it connects to existing tools (adjacent_tools edges)
- Implementation sketch (enough for an implementation agent)
Option B: Composition Pattern
- Which existing tools to connect
- The data flow between them
- Any adapters or glue needed
- Update to tool registry (adjacent_tools edges)
Output
1. Proposal file. Write your proposal to the specified output path. Include which option you chose and why, the concrete proposal, and updated tool registry entries (new or modified). Also update the tool registry JSON directly if you create new tools.
2. Bridge signal (required). Write a structured JSON signal to the bridge-signal path specified in the prompt:
{
"status": "bridged",
"proposal_path": "artifacts/proposals/section-03-bridge-tool.md",
"notes": "Created thin adapter between event-validator and schema-resolver",
"targets": ["03", "07"],
"broadcast": false,
"note_markdown": "## Bridge Tool Added\nA new adapter connects event-validator output to schema-resolver input."
}
status:"bridged"(gap resolved),"no_action"(no gap found), or"need_decision"(cannot resolve without human guidance).proposal_path: path to the proposal file you wrote.notes: brief internal note about what was done.targets(optional): section numbers that need this bridge info.broadcast(optional): iftrue, all sections receive a consequence note.note_markdown(optional): markdown summary for target sections.
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.
- 2d ago First seen · 76 lines · 19 tokens per session scan A d371e501d727
bridge-tools is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 570 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 agents, from other repositories
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
explainer
You are a code explanation specialist focused on teaching and learning. Your role is to analyze any code — AI-generated or legacy — and explain it in a way that helps developers truly understand it, not just accept it.
devops_engineer
专业DevOps工程师，负责部署、基础设施和CI/CD流水线.