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 haabe/mycelium/plugin install myceliumWrote 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/skills/haabe/mycelium/scaffold-cost-check)<a href="https://agentmods.dev/skills/haabe/mycelium/scaffold-cost-check"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/scaffold-cost-check/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/skills/haabe/mycelium/scaffold-cost-check"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/scaffold-cost-check.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 | $0.00047 | $0.01612 |
| Opus 5 | $0.00023 | $0.00806 |
| Sonnet 5 | $0.00009 | $0.00322 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
scaffold-cost-check 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 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.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Cost Check
Measure the token cost of Mycelium's stable scaffolding — the context surface loaded at SessionStart and on routine canvas/memory reads — so claims about "negligible overhead" are auditable. Datadog's State of AI Engineering (2026) reports ~69% of input tokens across production agents are system prompts; this skill makes Mycelium's analogous number visible.
When to Use
- First-time audit on a project to compare actual scaffold cost against any "~6K negligible" claim in landscape/positioning.
- Periodic refresh via
/mycelium:framework-health(see Wiring below). - Before adding a new canvas file or harness doc that joins the stable load surface, to surface the marginal cost.
Preflight: Read target canvas file(s) before any Write/Edit
Hard rule. Before issuing Write or Edit against any .claude/canvas/*.yml, use the Read tool on that file in this session. This skill only WRITES if explicitly asked to persist its output to dora-metrics.yml#apex.scaffold_token_estimate; default behavior is print-only.
Workflow
- Inventory the stable scaffold surfaces in the current project's plugin cache (or fall back to
.claude/for legacy installs):CLAUDE.md(project-local; the dispatcher)${CLAUDE_PLUGIN_ROOT}/engine/(all.mdand.yml)${CLAUDE_PLUGIN_ROOT}/harness/(all.md)AGENTS.md(project-local, if present — the router for non-Claude-Code runtimes; not a plugin file. It lives at a repo root and is never packaged, so resolving it through the plugin cache always missed and the row silently vanished from the table via the "if present" clause. Report0 / absentexplicitly when the project has none, rather than omitting the row — an omitted row reads as "not part of the surface" instead of "not there").claude/canvas/(project state — not framework, but it ALSO joins the load surface; report separately).claude/memory/(corrections.md, patterns.md, MEMORY.md)
- Sum bytes per surface via
wc -c. - Convert bytes → tokens via the 4-bytes-per-token heuristic (±15% for English markdown across OpenAI/Anthropic tokenizers). Document the heuristic + the uncertainty band in the output.
- Render the output block (see Output below).
- Optional: persist to canvas if the user passes
--write. Path:.claude/canvas/dora-metrics.yml#apex.scaffold_token_estimate. Follow the Postflight discipline below.
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 · 108 lines · 47 tokens per session scan A 0ec09e89607d
scaffold-cost-check is a skill published in the GitHub repository haabe/mycelium (45 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,612 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 skills, from other repositories
discovery
Capture interesting finds to the Vault via Inngest. Triggers when the user shares a URL, repo, or idea with signal words like "interesting", "cool", "neat", "check this out", "look at this", "came across", or when sharing content with minimal context that implies it should be remembered. Also triggers on bare URL…
knowledge-generator
Generates and accumulates structured project knowledge during the delivery process. Produces design baseline documents, ADRs, and project CLAUDE.md from Agent activities.
live-neon-persona
Manage AI agent identities on the Live Neon platform — fetch identity, sync content, run discovery, review beliefs, build prompts.
retrospective
Store a learning — classify type, route to canonical destination. Use after discoveries, unexpected issues, workarounds, or when a reusable pattern emerges.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…