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/kenn-io/agentsview/s3-providersgit clone --depth 1 https://github.com/kenn-io/agentsviewWhat 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 | $0.00000 | $0.00848 |
| Opus 5 | $0.00000 | $0.00424 |
| Sonnet 5 | $0.00000 | $0.00170 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
s3-providers 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
S3 Provider Rules
Read this file before enabling S3 ingest for an agent, changing S3Provider /
Source.S3Discovery, or altering S3 discovery, session IDs, temp
materialization, or post-fetch hydrate.
Operator configuration and object layouts live in docs/configuration.md under
S3-Compatible Session Sources. This guide is the implementer contract.
When S3 Fits
S3 ingest is for single-file session objects under:
s3://<bucket>/.../<machine>/raw/<agent>/...
The <agent> path segment must be the provider's AgentType string. The engine
uses that segment plus Source.S3Discovery to decide which objects belong to
which agent. Multi-file containers, SQLite stores, and agents that cannot name a
session from one object path do not belong here.
Required Surface
- Implement
parser.S3Providerininternal/parser/s3_provider.go. - Set
Source.S3DiscoverytoCapabilitySupportedon both the factory and the constructed provider. Startup migration rejects the capability if the provider does not implement the interface. - Route
s3://roots inDiscover/DiscoverEachthroughs3PrefixScan(root, scanner)so provider discovery and engine dispatch use the same keep/project rules. - Skip
s3://roots inWatchPlan. Object storage is not a local watch tree.
Default Versus Custom
Embed DefaultS3Provider when the agent matches the common layout:
- Keep objects whose names end in the declared extensions.
- Project is the first path segment under the configured root.
- Session ID is
IDPrefixplus the filename stem. - Temp path strips
raw/<agent>. - No sidecar folding and no post-fetch hydrate.
Write a dedicated <agent>_s3.go when any of those rules is wrong. Current
custom implementations:
| Agent | Why it cannot use the default alone |
|---|---|
| Claude | Sidecar fold, subagent paths, transcript keep rules |
| Codex | rollout-*.jsonl keep, codex: UUID IDs, sessions/archived rewrite, parent and session_index locate. TraeX shares the type and must not enable S3. |
| Cursor | Harvest <project>/<id>.{jsonl,txt} plus local agent-transcripts layouts; decode encoded project dirs only for the local layout; deduplicate a session stem across configured roots by source machine, preferring .jsonl, nested over flat, then lexical path |
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.
- yesterday First seen · 83 lines · 0 tokens per session scan A dd5c05b91e1f
s3-providers is an agent published in the GitHub repository kenn-io/agentsview (5,632 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 848 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 2026-08-30.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.