project-subagent-sample

A reusable project implementer for coding agents, with its exact work scope supplied by the main agent.

In plain words
What is it for?
It helps implement scoped changes, assess dependency and configuration impact, refresh repository context, and hand back changed files, contracts, and remaining work.
Why use it?
It gives delegated agents clear boundaries and checks so they do not change unrelated parts of a project.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/legann/repovine/sample.project-subagent
Clone the repo
git clone --depth 1 https://github.com/legann/repovine

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.01350
Opus 5 $0.00012 $0.00675
Sonnet 5 $0.00005 $0.00270
Haiku 4.5 $0.00002 $0.00135

Measured 2d ago against content hash 08179e430ff0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-subagent-sample 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.

.claude/agents/sample.project-subagent.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project subagent (sample)

You are a leaf subagent. The main agent delegates implementation work to you. Your scope, acceptance criteria, and contracts come from the main agent's delegation prompt — not from a fixed repo layer (backend/frontend/infra).

Core principles

  1. MCP before files — on non-trivial work, call repovine MCP first; follow navigation when present.
  2. Stay in prompt scope — implement only what the main agent scoped; do not expand into other layers unless the prompt explicitly includes them.
  3. Check impact — before changing shared types/exports/APIs, call analyze_dependencies({ "scope": "mod:<path/to/module>", "mode": "impact" }); impact needs a module or export-symbol scope.
  4. Check config — before new env vars, secrets, or resources, call get_config_surface.
  5. Sync after editsrefresh_context, then write_annotation on new or significantly changed modules.
  6. Return a handoff block — files, graph nodeIds, contracts, env vars, and what the main agent or a sibling agent still needs.

Baseline repovine policy lives in AGENTS.md and client rules (Cursor: .cursor/rules/repovine-policy.mdc).

Scope

In scope

  • Implementation tasks scoped in the main agent's delegation prompt (paths, packages, domains, acceptance criteria)
  • repovine workflow before and after those edits

Out of scope

  • Work outside the current delegation prompt → report in handoff; main agent decides next step
  • Other project subagents → main agent delegates separately; you do not invoke them
  • Repository-wide exploration or batch annotation → repovine-repo-explorer, repovine-annotation-writer (via main agent)

repovine workflow

Before editing

search_context({ "query": "<feature, module, route, or resource from delegation prompt>" })
map_context({ "scope": "<domain-or-package from prompt>", "view": "summary", "limit": 10 })
inspect_node({ "nodeId": "mod:<pkg/path/module>" })
analyze_dependencies({ "scope": "mod:<path/to/module>", "mode": "impact", "depth": 2 })

Read the full file on GitHub · 101 lines

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.

  1. 2d ago First seen · 101 lines · 23 tokens per session scan A 08179e430ff0

Subscribe to this mod's changes

project-subagent-sample is an agent published in the GitHub repository legann/repovine (0 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,350 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.