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 kucherenko/gangsta --skill the-ledgergit clone --depth 1 https://github.com/kucherenko/gangstaWrote 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/kucherenko/gangsta/the-ledger)<a href="https://agentmods.dev/skills/kucherenko/gangsta/the-ledger"><img src="https://agentmods.dev/badge/skills/kucherenko/gangsta/the-ledger/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/kucherenko/gangsta/the-ledger"><img src="https://agentmods.dev/badge/skills/kucherenko/gangsta/the-ledger.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.00974 |
| Opus 5 | $0.00018 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
the-ledger 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Ledger: Institutional Memory of the Gangsta Agents Family
Overview
The Ledger is the Gangsta Agents Family's persistent memory. It stores successful reasoning pathways (Insights), documented failures (Fails), and accumulated governance rules (the Project Constitution). Every Heist reads from and writes to the Ledger.
Directory Structure
The Ledger lives in the target project, NOT in the gangsta package:
docs/gangsta/
├── constitution.md # Project Constitution (living document)
├── insights/ # Repository of Insights (Good Catches)
│ └── YYYY-MM-DD-<topic>.md
└── fails/ # Repository of Fails (Concrete Shoes)
└── YYYY-MM-DD-<topic>.md
Initializing the Ledger
If docs/gangsta/ does not exist in the target project, create it:
mkdir -p docs/gangsta/insights docs/gangsta/fails
Create an initial docs/gangsta/constitution.md:
# Project Constitution
## Commandments (from Insights)
_No commandments yet. They will be added as Heists produce insights._
## Negative Constraints (from Fails)
_No constraints yet. They will be added as Heists document failures._
## Architectural Decisions
_No decisions recorded yet._
Writing an Insight
Criteria: Record when a solution bypasses a complex constraint, discovers a non-obvious approach, or establishes a new Project Commandment.
File: docs/gangsta/insights/YYYY-MM-DD-<topic-slug>.md
---
date: YYYY-MM-DD
heist: <heist-name>
phase: <phase-where-discovered>
tags: [tag1, tag2, tag3]
---
# <Title: Short description of the insight>
## Discovery
<How the insight was found — which phase, what triggered it>
## Solution
<The successful reasoning pathway or creative solution>
## Project Commandment
<If applicable: a new rule to add to the Constitution>
<If not applicable: omit this section>
After writing, update docs/gangsta/constitution.md:
- Add the commandment (if any) to the "Commandments" section
- Include source reference:
— Source: insights/YYYY-MM-DD-<topic>.md
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 · 131 lines · 36 tokens per session scan A c2e5afb22ace
the-ledger is a skill published in the GitHub repository kucherenko/gangsta (81 stars, last pushed 27d ago), licensed MIT. It adds 36 tokens to every session and 974 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
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
cocohealth
Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.
pod-resume
Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.
pull-search
CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.
pod-kb
Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.
wisdom-keep
Protect a CocoWisdom entry from consolidation. Usage: $wisdom keep --id --text " ".