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-code-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-code-debt)<a href="https://agentmods.dev/agents/tacoda/keystone/keystone-code-debt"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/keystone-code-debt/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/tacoda/keystone/keystone-code-debt"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/keystone-code-debt.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 | $0.00038 | $0.00514 |
| Opus 5.5 | $0.00015 | $0.00206 |
| Sonnet 5.5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
keystone-code-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 2mo 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
94% identical to code-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.
What it actually says
Sensor: code-debt
Surfaces and categorizes debt in the codebase — the known-suboptimal code the team has chosen to live with, plus the shape of any new debt being added in the current diff.
Paired sensor: charter-debt — covers debt in the charter itself (stale rules, placeholder bootstrap, empty idiom dirs, etc.). The two are tracked separately on purpose.
- Trigger — audit (codebase-wide) and review (diff-scoped).
- Inputs —
git grepfor debt markers (TODO,FIXME,HACK,XXX,DEPRECATED), complexity hotspots from risk-fingerprint, and any debt items already listed incorpus/state/code-debt.md. - Exit condition — every surfaced item is categorized (see Categories) and either matched to an existing ledger entry or proposed as a new one.
- Output — table of debt items: location, category, severity, owner (if known), whether new in this diff.
- State writes — proposes a diff to
corpus/state/code-debt.md. User accepts or edits.
Categories
| Category | What it means |
|---|---|
| deliberate | Known-suboptimal, chosen as a tradeoff. Has an owner and a trigger for revisit. |
| drift | Was once fine; the surrounding code moved and left this stale. |
| shortcut | A recent shortcut taken under time pressure. |
| discovery | Newly noticed; not yet categorized. |
A TODO without a category is automatically discovery until debt-review triages it.
Severity
- load-bearing — change is dangerous; the surrounding region depends on this exact shape.
- noisy — adds review burden but doesn't constrain change.
- stale — no longer relevant; can be removed without thought.
Anti-noise rule
Don't surface TODO in vendored or generated code (anything excluded from lint). Don't surface debt the ledger already records unless its severity changed.
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.
- 2mo ago First seen · 40 lines · 38 tokens per session scan A 4dd70a86dccd
keystone-code-debt is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 514 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to code-debt, differing in 7 lines, and is treated as a copy.
Other agents, from other repositories
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
swiftui-performance-analyzer
Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
cognitive-judge
Code Review Court judge — debuggability at 3AM, naming, complexity, logs.
silent-failure-hunter
Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…