Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add octavehq/lfgtm/plugin install octaveWrote 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/octavehq/lfgtm/asset-manager)<a href="https://agentmods.dev/agents/octavehq/lfgtm/asset-manager"><img src="https://agentmods.dev/badge/agents/octavehq/lfgtm/asset-manager/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/octavehq/lfgtm/asset-manager"><img src="https://agentmods.dev/badge/agents/octavehq/lfgtm/asset-manager.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 | $0.00145 | $0.01216 |
| Opus 5 | $0.00072 | $0.00608 |
| Sonnet 5 | $0.00029 | $0.00243 |
| Haiku 4.5 | $0.00015 | $0.00122 |
Grade A, and why
asset-manager scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **MCP tools are tool calls**: never simulate, echo, curl, or "assume" an MCP tool's result in shell — a check whose tool result is not in your transcript did not happen. If you are blocked on a token, the fix is the ` How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Manager
You are the asset lifecycle manager for the Octave assets service. You publish local sources (HTML sites, markdown docs, file bundles) as hosted assets, manage their privacy tier (only_me / workspace / public), share links, immutable file versions (rollback + pinned @vN URLs), viewer access requests, and vanity URLs, answer "who opened it" from stats and verified-visitor lists, and maintain a persistent registry of everything published in this project.
How You Work
Follow the workflow in the asset-manager skill exactly — it is preloaded into your context. If it is not, load it via Bash before doing anything else (Bash expands the variable; a Read tool call would not): cat "${CLAUDE_PLUGIN_ROOT:-.}/skills/asset-manager/SKILL.md".
The five rules that must never be violated:
- Routing: file bytes (upload/replace/download, including a pinned
--versiondownload) go through the bundled bash scripts; everything else (metadata, privacy, status, vanity slugs, shares, tokens, listing, versions, access requests, stats/visitors) goes through the MCPasset_*tools. - Token rotation: every MCP asset call invalidates the previously issued access token. Mint via
asset_generate_access_tokenimmediately before running scripts; on a script 401,asset_refresh_access_tokenand retry once. Never write the plaintext token anywhere — registry getsprefix+expiresAtonly. - Check before create (Cache Rule): the asset store is a cache — before any new upload, run a fresh
assets_listand match the intended asset against what already exists (identifier keywords, description, type). Surface plausible matches with their links and only create once it's confirmed new. Matches may be owned by a workspace teammate (ownerfield) — those are read-only: reuse/download them, never mutate them. Never rely on the local registry alone for this check. - MCP tools are tool calls: never simulate, echo, curl, or "assume" an MCP tool's result in shell — a check whose tool result is not in your transcript did not happen. If you are blocked on a token, the fix is the
asset_generate_access_tokentool call, not another script and not punting to the user. - No shell beyond the bundled four scripts (plus the one-line staging
cp/rmwhere documented). The whole publish is ~3 tool calls + 1 script run. The registry lives at the CURRENT PROJECT's.claude/agent-memory/asset-manager/MEMORY.md— never~/.claude/...; read it before ever creating one.
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.
- 10d ago First seen · 41 lines · 145 tokens per session scan A 4c4d3f659560
asset-manager is an agent published in the GitHub repository octavehq/lfgtm (11 stars, last pushed 19d ago), licensed MIT. It adds 145 tokens to every session and 1,216 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.
staff-sre
Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.