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 commands/tacoda/keystone/debt-reviewgit 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/commands/tacoda/keystone/debt-review)<a href="https://agentmods.dev/commands/tacoda/keystone/debt-review"><img src="https://agentmods.dev/badge/commands/tacoda/keystone/debt-review.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 | $0.00008 | $0.00412 |
| Opus 5 | $0.00004 | $0.00206 |
| Sonnet 5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
debt-review 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- keystone-debt-review — 94% identical, 4 lines differ
What it actually says
debt-review
Triage the code-debt ledger. Read .charter/sensors/code-debt.md and .charter/corpus/state/code-debt.md.
For charter debt (stale rules, placeholder bootstrap, empty idiom dirs, uncited policies), use the audit action — its Pruning flywheel writes to corpus/state/charter-debt.md.
Activities
- Run the code-debt sensor. Walk the codebase for markers and complexity hotspots; produce the candidate list.
- Triage
discoveryitems. For each, propose: a category (deliberate / drift / shortcut), a severity, an owner, and a revisit trigger. If you can't propose all four, leave the item asdiscoverywith a note explaining why. - Re-score existing items. Compare ledger entries against the code. Items whose region is no longer present, or whose severity has dropped to nothing the diff or plan would notice, become
stale. - Prune
staleitems. Delete them from the ledger. Do not archive. - Propose the diff to
corpus/state/code-debt.mdand let the user accept or edit. No silent writes.
When to invoke
- Periodically (suggested: monthly or per audit pass).
- Before any large refactor of a region with multiple ledger entries — to make sure the plan accounts for them.
- When the ledger has accumulated more than ~10
discoveryitems.
Output
One report:
- Items triaged (with proposed category/severity/owner/trigger).
- Items pruned as
stale. - Items re-scored.
- Open questions where triage stalled.
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.
- 6d ago First seen · 34 lines · 8 tokens per session scan A 786937124828
debt-review is a command published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 412 once invoked, about $0.0000 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 commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.