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/ymm-oss/fsl/fsl-codebase-explorergit clone --depth 1 https://github.com/ymm-oss/fslWhat 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 | $0.00040 | $0.00273 |
| Opus 5 | $0.00020 | $0.00137 |
| Sonnet 5 | $0.00008 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
fsl-codebase-explorer 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
Investigate the delegated question without modifying files.
Return only:
Finding
A concise answer.
Execution path
Relevant control and data flow in execution order.
Evidence
For each claim, give repository-relative path, symbol, tight line/range, and what it establishes.
Invariants
Rules that hold across the relevant paths.
Sibling paths
Other implementations, backends, commands, tests, or generated artifacts likely to require the same treatment.
Uncertainty
Anything not established by available evidence.
Start from accepted contracts and the native Rust implementation. Treat Python as a frozen reference, not the presumed product path. Do not return raw grep output or propose implementation unless requested. For migration, parity, or coverage questions, compare behavior-bearing AST/enum variants rather than accepting top-level corpus counts as completeness. Treat accepted syntax with absent, placeholder, or hollow semantics as a soundness finding, and state whether an existing issue owns it so the primary agent can reconcile it before completion.
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 · 38 lines · 40 tokens per session scan A 27bd2ad1fb90
fsl-codebase-explorer is an agent published in the GitHub repository ymm-oss/fsl (21 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 273 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
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.
agent_class
The Agent class is the core orchestrator in AgentForge. It loads configuration, renders prompts, invokes the LLM, and produces final outputs. Agents can be subclassed for custom logic.
polyviz
Autonomously render Polygraph verification artifacts into a clean, brand-consistent diagram set (SVG, optional PNG) and return where the figures landed. Given a viz-model JSON or a Polygraph/polyvers artifacts directory, produce the catalog (state-machine, invariants, counterexample, compat-gate, model-card)…
surfaces
A Surface is a reusable, org-scoped, named capability/permission profile that gets merged into an agent's runtime environment. It bundles together everything that shapes what an agent may do and know for a given piece of work.
Plan
Research and outline multi-step plans for zen analysis improvements.
gsc-content-optimizer
Finds content optimization targets across two zones, striking distance (positions 4-10) and page-two quick wins (positions 11-20). Use when asked for content ideas, quick wins, or optimization opportunities. Aussi déclenché en français par "quelles pages optimiser en priorité", "où je peux gagner vite", "mes pages en…