Borrowing it
Nothing to install: this file belongs to tacoda/keystone. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tacoda/keystone/main/.claude/agents/keystone-charter-debt.mdgit clone --depth 1 https://github.com/tacoda/keystoneWrote 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/tacoda/keystone/keystone-charter-debt)<a href="https://agentmods.dev/agents/tacoda/keystone/keystone-charter-debt"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/keystone-charter-debt.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 | $0.00024 | $0.00766 |
| Opus 5 | $0.00012 | $0.00383 |
| Sonnet 5 | $0.00005 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
keystone-charter-debt 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 8d 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.
This is a copy
95% identical to charter-debt — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sensor: charter-debt
Surfaces debt in the charter itself — content that exists but isn't earning its keep. Distinct from code-debt, which covers debt in the codebase.
- Trigger — audit (full sweep). Cheaper subsets can run on demand.
- Inputs —
.charter/tree,.charter/corpus/state/CODEBASE_STATE.md,.charter/.keystone.lock,git log -- .charter/, and the outputs of the sensors classified as available inCODEBASE_STATE.md. - Exit condition — every category below has been swept; each finding is matched to an existing ledger entry or proposed as a new one.
- Output — table of charter-debt items: location, category, severity.
- State writes — proposes a diff to
corpus/state/charter-debt.md. User accepts or edits.
Categories
| Category | What it means | How to detect |
|---|---|---|
| stale-rule | A guide no diff has touched in N months. | git log --since=N.months.ago -- .charter/guides/<file> is empty. |
| dead-idiom | An idiom directory for a stack no longer in CODEBASE_STATE.md. |
Compare .charter/corpus/idioms/* against detected stacks. |
| placeholder | Bootstrap placeholders (<...>) left unfilled. |
grep -rE '<[^>]+>' .charter/corpus/state/. |
| failing-sensor | Sensor classified as available in CODEBASE_STATE.md but errors when invoked. |
Try the recorded command; record exit code. |
| empty-shell | Directory scaffolded by bootstrap (idioms, learning/inbox) that has no real content. | Directory size + non-README file count. |
| uncited-policy | Installed policy whose guides were never referenced in the last N reviews. | Cross-reference policy guide paths against review outputs (or git log of review reports). |
| unresolved-gap | .charter/adapters/<agent>/<topic>.md left as a TODO placeholder past install. |
grep -r 'TODO' .charter/adapters/. |
| drifted-state | CODEBASE_STATE.md last_reconciled is older than N months OR stack-drift sensor flagged divergence. |
Frontmatter date + stack-drift output. |
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.
- 8d ago First seen · 44 lines · 24 tokens per session scan A 3eac59522e2d
keystone-charter-debt is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 766 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to charter-debt, differing in 7 lines, and is treated as a copy.
Other agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
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.
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.