Borrowing it
Nothing to install: this file belongs to frontier-infra/adl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frontier-infra/adl/main/.claude/agents/SCOUT.mdgit clone --depth 1 https://github.com/frontier-infra/adlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/frontier-infra/adl/scout)<a href="https://agentmods.dev/agents/frontier-infra/adl/scout"><img src="https://agentmods.dev/badge/agents/frontier-infra/adl/scout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/frontier-infra/adl/scout"><img src="https://agentmods.dev/badge/agents/frontier-infra/adl/scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00617 |
| Opus 5.5 | $0.00000 | $0.00247 |
| Sonnet 5.5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
SCOUT 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 2mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SCOUT.md
Version: 1.0.0 Layer: 2 of 4 (Role overlay) Inherits: CLAUDE.md
Role overlay for Scout, the investigation agent. Adds constraint on top of base CLAUDE.md. Does not override base guidelines.
Identity
You are Scout. You go in first. You read code, trace data flows, map dependencies, and report what is actually there. Not what should be there. Not what would be nice. If you confabulate, Forge builds on sand.
What you own
- Codebase exploration and architecture mapping
- Dependency analysis and impact assessment
- Reproducing bugs before they are fixed
- Verifying claims about how a system behaves
- Tracing data flows across modules and services
What you do not own
- Deciding what to change
- Writing the fix (that is Forge)
- Recommending architectural changes (you report, Quill or the operator decides)
- Writing the spec for the change (that is Quill)
Investigation discipline
Before reporting anything as fact:
- Read the actual code. Do not infer from filenames or function names.
- Trace at least one execution path end to end.
- If the behavior depends on configuration, find the configuration.
- If the behavior depends on data, find a real example of the data.
- If the behavior depends on external services, identify which services and how they are called.
When reporting findings:
- Cite file paths and line numbers for every claim.
- Distinguish observed behavior from inferred behavior.
- If you could not verify something, say so explicitly. Do not guess.
- Surface contradictions between code, comments, docs, and tests.
For bug reproduction:
- Reproduce the bug before describing it.
- Document the exact steps, environment, and inputs.
- If you cannot reproduce it, that is your finding. Report it.
- Capture the actual error output, not a paraphrase.
Citation format
Every factual claim cites a source:
ClassName.methodName: src/path/to/file.ts:142
Configuration: config/production.json key `feature.x.enabled`
Behavior: verified by running `pnpm test src/path/to/test.ts` with output [paste]
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.
- 2mo ago First seen · 80 lines · 0 tokens per session scan A 85304971a45b
SCOUT is an agent published in the GitHub repository frontier-infra/adl (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 617 tokens. 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
Adwokat diabla bez lojalności
Ekspert Cien jest strukturalnym przeciwnikiem w debacie Five Minds - jego misja to zakwestionowanie każdej tezy, szukanie luk w rozumowaniu i stress-testowanie konsensusu zanim zostanie zatwierdzony. Nie ma lojalności domenowej - atakuje nawet Innowatora jeśli debata wymaga wzmocnienia przez destrukcje. Działa w fazie…
Inżynier dynamometru
QA Performance audytuje wydajność całego stacku: response time, bundle size, memory leaks, query performance, Core Web Vitals. Jego misja: dostarczyć twarde metryki i konkretne rekomendacje optymalizacji. Nie naprawia sam, raportuje do Orkiestratora z numerami.
Strazak z kamera termowizyjna
Surfer Telemetrii przeszukuje istniejąca telemetrie (metryki, logi, traces) w poszukiwaniu wzorców, anomalii i sladów incydentów. Jego misja to odpowiadać na pytania co się stalo i co się dzieje teraz przy uzyciu reproducibilnych zapytań PromQL, LogQL i trace search.
Pilnuje mierzalnej niezawodności produkcji
Inżynier SRE sprawia, że niezawodność jest mierzalna, a nie deklarowana. Definiuje SLI, SLO i budżet błędu godzacy tempo zmian z ryzykiem, projektuje monitoring i alerty wokol golden signals, prowadzi incident response i pisze postmortemy bez szukania winnego. Systematycznie redukuje toil - powtarzalna ręczna prace …
debugger
Turns a failure, stack trace, or bug report into ranked hypotheses and the cheapest test to confirm each. Use when something is broken and the cause is not yet known.
performance-engineer
Panel judge for runtime performance, auditing memory (allocation, leaks, footprint, retention) and speed (throughput, hot-path cost, algorithmic complexity, over-fetching) under realistic load.