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 skills add gtapps/claude-code-hermit --skill story-arcsgit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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/gtapps/claude-code-hermit/story-arcs)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/story-arcs"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/story-arcs.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00849 |
| Opus 5 | $0.00029 | $0.00425 |
| Sonnet 5 | $0.00012 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
story-arcs 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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Arcs
Manage the developing-story-arcs file that feeds the feed-brief arc-tagging enrichment.
Usage
/story-arcs add "<name>" [--started <YYYY-MM-DD>] [--watch "<keywords>"] [--context "<text>"]
/story-arcs resolve "<name>" [--reason "<resolution note>"]
/story-arcs list
Steps
1. Find the active arcs file
Glob .claude-code-hermit/compiled/story-arcs-*.md. Sort by filename date suffix descending (newest first). Read the most
recent. If none exists, create .claude-code-hermit/compiled/story-arcs-<today>.md with the standard template
(frontmatter + ## Active + ## Recently Resolved sections).
2. Execute subcommand
add
Parse: name (required), --started (default: today, prefixed with ~), --watch (optional keyword list), --context (optional description).
- Check
## Active— if an arc with the same name already exists (case-insensitive), say so and stop. - Append a new arc block at the end of
## Active:**<name>** (started: ~<YYYY-MM-DD>) <context text, or "Newly surfaced — add context as it develops."> Watch: <watch keywords separated by semicolons, or "TBD">. - Write the file in-place. Reply:
Arc added: **<name>**. Update the Watch clause with /story-arcs if needed.
resolve
Parse: name (required, case-insensitive substring match), --reason (optional).
- Find the arc block in
## Active. If not found, list close matches and stop. - Remove the full arc block (the
**Name** (started:...)line + context line + Watch line). - Insert a one-line entry at the top of
## Recently Resolved:**<name>** — <reason, or "resolved">. <today's date> - Write the file in-place. Reply:
Arc resolved: **<name>**. It will no longer be matched in future briefs.
list
- Display all arcs under
## Activeas a compact table: Name, start date, Watch keywords. - Show the count of
## Recently Resolvedentries. - If
## Activeis empty, say "No active arcs."
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.
- 4d ago First seen · 92 lines · 58 tokens per session scan A 6a132ccc17b2
story-arcs is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 849 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
magic-compact
Compact this Claude Code session.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
subagent-output-templating
Template for structured sub-agent output including YAML log format, task completion reports (WHY/WHAT/TRADE-OFFS/RISKS), and summary constraints. Use when defining how sub-agents should report results.