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 atuljha23/holocron --skill token-economygit clone --depth 1 https://github.com/atuljha23/holocronWrote 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/atuljha23/holocron/token-economy)<a href="https://agentmods.dev/skills/atuljha23/holocron/token-economy"><img src="https://agentmods.dev/badge/skills/atuljha23/holocron/token-economy/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/atuljha23/holocron/token-economy"><img src="https://agentmods.dev/badge/skills/atuljha23/holocron/token-economy.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 | $0.00051 | $0.01088 |
| Opus 5 | $0.00026 | $0.00544 |
| Sonnet 5 | $0.00010 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
token-economy 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 11d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token economy
Three things drive cost in Claude Code: context size, cache hit rate, and model choice. Most waste comes from one of these being misconfigured and left alone.
Model tiering — match the model to the task
| Task shape | Right model |
|---|---|
| Format fix, rename, small refactor, comment tweak | Haiku — ~15× cheaper than Opus, fast enough to feel instant |
| Routine feature work, bug fix, test writing, reviewing a small diff | Sonnet — the default; 5× cheaper than Opus |
| Architectural decision, cross-file refactor, debugging a subtle bug, reviewing a large diff | Opus — use when you need the reasoning, not by default |
Claude Code's /fast or model selection lets you pick. Don't use Opus by reflex for a typo fix.
Cache hygiene — the 80% lever nobody talks about
Anthropic caches your prompt prefix for 5 minutes. A stable prefix = the next turn reads from cache at ~10% of input cost. A prefix that changes each turn = full price every time.
What busts cache:
- Timestamps in CLAUDE.md, in skill content, or in hook output
- Session IDs / UUIDs interpolated into system prompt
- Rotating "quotes of the day", random greetings
- MCP servers that return time-varying schema metadata
What preserves cache:
- CLAUDE.md that doesn't change day-to-day
- Skill/rule content that's additive, not mutating
- Hook
additionalContextthat's deterministic for a given input - Turning off MCP servers you don't need (every schema change invalidates cache)
How to check: /holocron:cost — the cache hit rate line. Below 50% is a signal; above 70% is healthy.
Read discipline — the most common leak
Claude's Read tool pulls whole files by default. A 2000-line file is ~8k tokens. Do that 5 times in a session and you've spent ~40k tokens reading the same file repeatedly.
Pattern:
Grepto find the relevant range (cheap — returns only matching lines)Readwithoffset+limitfor the range you identified
Holocron's read-budget.js hook nudges this on files > 500 lines, but the discipline has to be yours.
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.
- 11d ago First seen · 94 lines · 51 tokens per session scan A 9d553e767ae8
token-economy is a skill published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,088 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 2026-08-31.
Other skills, from other repositories
survey-generator
Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in /derived/surveys/…
batch-orchestration
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
design-engineering
Apply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when building a component, animation, transition, hover or press state, modal, drawer, toast, or when polishing an interface so it feels right. Says "make this feel better", "add an…
skill-optimizer
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably…
skill-router
The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".
sprint-status
Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.