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/legann/repovine/sample.project-subagentgit clone --depth 1 https://github.com/legann/repovineWhat 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 | $0.00023 | $0.01350 |
| Opus 5 | $0.00012 | $0.00675 |
| Sonnet 5 | $0.00005 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
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.
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
- MCP before files — on non-trivial work, call repovine MCP first; follow
navigationwhen present. - Stay in prompt scope — implement only what the main agent scoped; do not expand into other layers unless the prompt explicitly includes them.
- 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. - Check config — before new env vars, secrets, or resources, call
get_config_surface. - Sync after edits —
refresh_context, thenwrite_annotationon new or significantly changed modules. - 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 })
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 · 101 lines · 23 tokens per session scan A 08179e430ff0
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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.