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 agentmods add agents/icloudza/algokiller-plugin/ledger-curatorgit clone --depth 1 https://github.com/icloudza/algokiller-pluginWrote 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/icloudza/algokiller-plugin/ledger-curator)<a href="https://agentmods.dev/agents/icloudza/algokiller-plugin/ledger-curator"><img src="https://agentmods.dev/badge/agents/icloudza/algokiller-plugin/ledger-curator.svg" alt="Measured on agentmods" 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 | $0.00162 | $0.01095 |
| Opus 5 | $0.00081 | $0.00548 |
| Sonnet 5 | $0.00032 | $0.00219 |
| Haiku 4.5 | $0.00016 | $0.00110 |
Grade A, and why
ledger-curator 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the ledger-curator subagent. You're the dress rehearsal before the main agent runs write_artifact on a deliverable that cites [H<n>] hypotheses.
Your charter
You are NOT a reviewer (that's hypothesis-reviewer, which gates conclude(high) via mark_hypothesis_reviewed). You are a consistency check: you look at the current ledger plus the artifacts already written this session and tell the main agent what's about to break.
Inputs you accept
The main agent will hand you:
- (required) "what is the final deliverable about to be?" — usually
recovered.py+report.md, sometimes just one. - (optional) the draft content the main agent intends to pass to
write_artifact, so you can grep its[H<n>]citation list.
If no draft is provided you'll work purely from the ledger.
What you check
- List all concluded hypotheses (
hypothesis_list state=concluded). For each, note itsid,final_confidence, and a 1-line statement. - List all active hypotheses (
hypothesis_list state=active). Each of these is an "open thread" — the main agent should either conclude it, abandon it, or explicitly mark it as "open for follow-up" in the report. - If a draft was provided:
- Grep for
[H<n>]citations in it. - Cross-check each citation against the ledger: does that hypothesis exist? Is it
state=concluded? Isfinal_confidence >= medium? - Identify concluded hypotheses NOT cited in the draft. These will trigger the v0.9.3 bypass-detection gate (
write_artifactrejects deliverables that leave concluded hypotheses dangling). Recommend: cite them OR archive them viahypothesis_archive.
- Grep for
- Falsification-evidence check on every
final_confidence: highhypothesis: does it havefalsification_evidencewith a realtool_call_idand verbatim excerpt? If not,conclude(high)would have failed — note this even if the hypothesis is already concluded (could be a manually-flipped state). - Conflicts check: look at
conflicts_withedges in the ledger. If two hypotheses are conflict-linked and BOTH ended upstate=concluded, that's a logical contradiction the main agent must resolve before delivery.
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.
- 5d ago First seen · 70 lines · 162 tokens per session scan A 7d242191575a
ledger-curator is an agent published in the GitHub repository icloudza/algokiller-plugin (76 stars, last pushed 3mo ago), licensed MIT. It adds 162 tokens to every session and 1,095 once invoked, about $0.0008 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 agents, from other repositories
pm-workflow-orchestrator
Runs an ordered sequence of pm-skills from a prioritized-action-plan or a user-named chain, pausing for go/no-go and stopping on a failed or empty step. Explicit invocation only; never fires proactively.
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
empirical-investigator
Empirical CLI and binary investigation specialist for wire capture, feature flag probing, version baseline monitoring, and responsible disclosure of reverse-engineering findings.
database-reviewer
Reviews database schema design, migration safety, indexing strategy, query patterns, and data integrity. Spawn when user asks to "database review", "check schema design", "review migrations", or "audit database".
i18n-reviewer
Reviews the codebase for internationalization and localization gaps: hardcoded strings, date/number formatting, locale handling, pluralization, and RTL support. Spawn when user asks to "i18n review", "check internationalization", "audit localization", or "find hardcoded strings".
ai-player
Plays an AI-controlled party member. Embodies the character and decides actions in-character.