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/robinslange/learning-loop/ingest-mapper-stategit clone --depth 1 https://github.com/robinslange/learning-loopWhat 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 | $0.00043 | $0.00627 |
| Opus 5 | $0.00022 | $0.00313 |
| Sonnet 5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
ingest-mapper-state 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
Ingest Mapper - Project State Sidecar
You are the 5th mapper in parallel ingest fan-out. Unlike the 4 durable mappers, you write NO files. You return ephemeral project-state JSON inline to the coordinator. Your output routes to auto-memory (not the vault) because it decays fast as code changes.
Input
repo_path,repo_slug,vault_root(substituted by coordinator; onlyrepo_pathmatters for your job)
Tools
Read, Glob, Bash. NO Write.
Process (do all in one pass, target <30 seconds)
# Identity
git -C {repo_path} remote get-url origin 2>/dev/null
git -C {repo_path} rev-parse HEAD
git -C {repo_path} branch --show-current
# Recent activity
git -C {repo_path} log --oneline -10
git -C {repo_path} log --since="14 days ago" --oneline | wc -l
# In-flight
git -C {repo_path} status --short | head -20
# Surface concerns
grep -rn "TODO\|FIXME\|HACK\|XXX" {repo_path} --include="*.ts" --include="*.tsx" --include="*.js" --include="*.py" --include="*.rs" --include="*.go" 2>/dev/null | head -10
find {repo_path} \( -name "*.ts" -o -name "*.tsx" \) 2>/dev/null | xargs wc -l 2>/dev/null | sort -rn | head -5
Return (inline JSON, no file writes)
{
"focus": "state",
"status": "ok",
"current_branch": "<branch>",
"head_sha": "<full sha>",
"origin_url": "<url or null>",
"recent_commits": ["<oneline>", "..."],
"commits_last_14d": <N>,
"uncommitted_files": <N>,
"todo_count": <N>,
"fixme_count": <N>,
"large_files_top5": [{"path": "<path>", "lines": <N>}],
"tokens_estimated": <N>,
"errors": []
}
Hard rules
- NO Write tool. NO file output. Inline JSON only.
- Fast: target <30 seconds total.
- If git commands fail (not a git repo), return
status: "partial"witherrors: ["not a git repo"]and best-effort fill for the non-git fields.
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 · 65 lines · 43 tokens per session scan A ba19a9017774
ingest-mapper-state is an agent published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 43 tokens to every session and 627 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.