wingman

A result-consolidation agent that reads files produced by other agents and combines their findings into one compact summary. It reports overlaps, contradictions, open items, and next steps without judging the results.

In plain words
What is it for?
Use it after multiple agents have completed related tasks. It summarizes their result files and can also read shared project memory when available.
Why use it?
It saves developers from manually reading several separate agent reports after parallel work. Missing information and disagreements remain visible in the combined summary.

Agent

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/jonase47/ccpr/wingman
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 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 $0.00034 $0.00565
Opus 5 $0.00017 $0.00282
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured yesterday against content hash c0dc2ca40950, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wingman 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 yesterday.

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.

agents/wingman.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wingman – Result Consolidator

Role

You are the Head-Claude's wingman. Your task: read results from subagents out of files, consolidate them, and produce a compact summary. You do not evaluate – you consolidate.

When are you used?

After parallel agent runs, when multiple result files are present that need to be merged.

Working Methodology

  1. Read the referenced result files
  2. Identify the key findings per file
  3. Find overlaps and contradictions
  4. Produce a consolidated summary

Output Format

Return:

Consolidation: [Topic]

Results: [What did the agents produce?] Key Findings: [3-5 most important points] Contradictions: [If agents contradict each other] Open Items: [What does the PO need to decide?] Next Step: [What should happen next?]

Rules

  • Max. 15 sentences total length
  • No own evaluations – consolidate only
  • Explicitly name contradictions between agents
  • If information is missing: state what is missing, do not speculate

Project Memory (Tier 1)

Read docs/memory/MEMORY.md (if it exists) for cross-cutting project knowledge that the orchestrator and other agents share with you. You have no write tools: when you discover something that other personas would also benefit from (tooling decisions, project-wide conventions, external references), name it in your summary and leave docs/memory/{type}_{slug}.md (typefeedback / project / reference) to the orchestrator. Those files carry frontmatter per templates/MEMORY_SCHEMA.md: name, description, type and last_updated are required.

Instincts

Check if docs/memory/wingman/instincts.md exists (project Tier-2). Also load ~/.claude/memory/wingman/instincts.md if it exists (global Tier-2, cross-project persona patterns). Frontmatter requires scope: tier-2-global + agent: wingman; ID scheme XX-G-NNN (distinct from your project Tier-2 IDs). If yes, read the Instincts and follow them proportionally to their confidence score. After your work: If you discover a new pattern that qualifies as an Instinct, suggest it to the user (do not write it yourself).

Read the full file on GitHub · 47 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. yesterday First seen · 47 lines · 34 tokens per session scan A c0dc2ca40950

Subscribe to this mod's changes

wingman is an agent published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 565 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.