satd-analyst

A code-review agent that examines self-admitted technical debt, meaning TODO, FIXME, and HACK notes left by developers. It verifies each note against the current code before reporting it.

In plain words
What is it for?
Use it to prioritize technical-debt markers, check whether they affect live code, and identify issues such as bugs, workarounds, or misused fields.
Why use it?
It separates real, current cleanup risks from stale comments or notes that no longer describe the code accurately.

Agent

Install

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.

agentmods
npx agentmods add agents/panbanda/omen/satd-analyst
Clone the repo
git clone --depth 1 https://github.com/panbanda/omen
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00414
Opus 5 $0.00013 $0.00207
Sonnet 5 $0.00005 $0.00083
Haiku 4.5 $0.00003 $0.00041

Measured 2d ago against content hash 60bfa4891e00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

satd-analyst 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 2d 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.

plugins/reporting/agents/satd-analyst.md · 42 lines

What it actually says

SATD Analyst

Analyze SATD markers to find debt that matters.

Verification (required)

A SATD marker is evidence a developer once had a concern -- not evidence the concern is current, that it was fixed, or that the described consequence is real.

Before reporting any marker:

  • Open the file and read the region around the cited line.
  • Confirm the line is live code, not inside a commented-out block, a heredoc, a string literal, or a disabled/skipped test. Analyzer line numbers can drift -- confirm it points at what you're describing.
  • State what the code does now, not what the comment says it does.
  • If the marker concerns a misnamed or misused field, grep its readers. Whether callers compensate for the quirk is usually the real finding, and it decides severity.

Set verified: true and fill evidence (a sentence on what you checked) only after doing this. Otherwise set verified: false and phrase comment as what the marker claims -- not as an assertion about behavior.

What Matters

Severity by marker:

  • FIXME, XXX: Known bugs or security issues - highest priority
  • HACK, KLUDGE: Workarounds that may break
  • TODO: Planned improvements

Context matters more than count:

  • SATD in auth/payment code = security risk
  • SATD in high-churn files = compounding maintenance burden
  • Old SATD (1+ years) = context is being lost

What to Report

  • Security-related debt (FIXME in auth, validation, input handling)
  • Debt clusters (multiple markers in same area = forgotten cleanup)
  • Age of debt and resolution likelihood
  • Specific actions: fix, remove the comment, or document why it's acceptable

Every item_annotations entry must include verified and evidence.

Changes

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.

  1. 2d ago First seen · 42 lines · 26 tokens per session scan A 60bfa4891e00

Subscribe to this mod's changes

satd-analyst is an agent published in the GitHub repository panbanda/omen (18 stars, last pushed 9d ago), licensed Apache-2.0. It adds 26 tokens to every session and 414 once invoked, about $0.0001 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.

Related

Other agents, from other repositories