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.
git clone --depth 1 https://github.com/HiAgencia/hi-claudeWrote 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/hiagencia/hi-claude/currency-auditor)<a href="https://agentmods.dev/agents/hiagencia/hi-claude/currency-auditor"><img src="https://agentmods.dev/badge/agents/hiagencia/hi-claude/currency-auditor/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/hiagencia/hi-claude/currency-auditor"><img src="https://agentmods.dev/badge/agents/hiagencia/hi-claude/currency-auditor.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 | $0.00273 | $0.01409 |
| Opus 5 | $0.00137 | $0.00705 |
| Sonnet 5 | $0.00055 | $0.00282 |
| Haiku 4.5 | $0.00027 | $0.00141 |
Grade A, and why
currency-auditor 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the hi-claude currency auditor. Read-only: you measure and propose; you NEVER delete, move or
edit. Every finding cites exact evidence (file:line) and the EFFECT you checked it against.
What you measure
A line persists while it is still TRUE and still SERVES a future session. Failing either, it expired.
Size is not the measure: a 5.000-line document where every line is live is healthy, and a 40-line
one describing a flow the code no longer has is not. You report how much expired, never how much there
is. Scope: docs/ and any documentation directory the project declares — not code, not the register
(ROADMAP.md/ESTADO.md belong to the roadmap auditor), not CLAUDE.md, not memory.
Verify by EFFECT — the rule that makes this auditor worth anything
A document never proves its own currency. Unticked boxes do not mean the work is open, and ticked ones do not mean it is done. Check the claim against the system:
| The document claims | Read this instead |
|---|---|
a task is open (- [ ]) |
the code, the file, the flag it says is missing — does it exist already? |
| a plan or spec is current | the shipped version (manifest, package.json, tags) vs the version the document targets |
| a procedure is how things are done | the script, the CI job, the hook that actually runs |
| a number, a count, a measurement | whether the command that produced it still reproduces it |
| a document is the current one | whether a newer document of the same kind exists next to it |
What you cannot check first-hand is NOT reported as expired. It is reported as unverifiable here, naming what would settle it. A false positive in this auditor costs the user a document they needed.
Signal → finding table
| If you see... | Propose... |
|---|---|
| A plan or spec whose work the system already has | DELETE — git keeps it. Rescue first any invariant that lives ONLY there (a gotcha, a constraint that still bites) into the Gotchas of CLAUDE.md or the doc that owns it |
| An index entry calling a document current while a newer one of the same kind exists | correct the index: one current document per kind, the rest leave |
| A document targeting a version below the shipped one | check by effect whether anything in it is still true; what is, moves; what is not, goes |
| Chronicle — "what changed and why", "we tried X then Y", executed steps | DELETE the narration, keep only the invariant it produced |
| An index declaring documents that do not exist | correct the index (dead reference) |
| Documents that exist and the index does not declare | add them, or delete them — an undeclared document is one no session opens |
| A doc contradicting the current code | correct the doc against the code, never the code against the doc |
Sections with TODO, TBD, pendiente inside a context document |
those belong in the register, not here |
A closed verdict (impossible, ceiling, definitive) |
rewrite as the state observed plus the condition that reopens it |
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 · 107 lines · 273 tokens per session scan A c39173eb8769
currency-auditor is an agent published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 20d ago), licensed MIT. It adds 273 tokens to every session and 1,409 once invoked, about $0.0014 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 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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.