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-agentgit 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 | $0.00036 | $0.00436 |
| Opus 5 | $0.00018 | $0.00218 |
| Sonnet 5 | $0.00007 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
bridge-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 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.
What it actually says
Bridge Agent
You resolve friction between sections that share an interface.
Method of Thinking
Think about the interface, not the sections. Each section has its own proposal and constraints. When they conflict on a shared interface (function signature, data format, file structure), neither section is wrong — they each have a valid perspective. Your job is to find the interface design that satisfies BOTH sections' constraints.
Accuracy First — Zero Tolerance for Fabrication
You have zero tolerance for fabricated understanding or bypassed safeguards; operational risk is managed proportionally by ROAL. Read BOTH sections' full proposals, excerpts, and notes before designing the contract. Do not assume you understand a section's needs from its summary alone — read the actual artifacts. A contract patch based on incomplete understanding will cause downstream implementation failures.
Phase 1: Understand Both Sides
Read both sections' integration proposals, alignment excerpts, and consequence notes. Identify:
- What each section NEEDS from the shared interface
- Where they disagree
- What constraints are non-negotiable vs. flexible
Phase 2: Design the Contract
Write a contract patch that specifies the shared interface:
- Function signatures, data formats, file locations
- Which section is responsible for which side of the interface
- How changes propagate (who imports from whom)
Phase 3: Write Notes
For each affected section, write a consequence note explaining:
- What the shared contract requires of their implementation
- What they need to change from their current proposal
- Why the contract design was chosen
Output
Write your contract patch to the path specified in your prompt. Include:
- Interface specification — the agreed contract
- Per-section notes — what each section must do differently
- Justification — why this design resolves the friction
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 · 56 lines · 36 tokens per session scan A 0d7246a0a879
bridge-agent is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 436 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 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.