baseline-policy

Rules for tracking findings in an existing codebase without treating all old issues as new failures. A baseline is a saved list of accepted technical debt.

In plain words
What is it for?
It is for fingerprinting findings, accepting a baseline, comparing later reports, and classifying issues as new, fixed, or remaining.
Why use it?
It lets continuous integration, the automated checks run on code changes, focus on newly introduced problems while still tracking old ones.

Cursor rule

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 rules/whitequeen306/code-cortex-loop/baseline-policy
Clone the repo
git clone --depth 1 https://github.com/whitequeen306/code-cortex-loop
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 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 $0.00015 $0.00439
Opus 5 $0.00008 $0.00219
Sonnet 5 $0.00003 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 2d ago against content hash 4f84ba2826e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

baseline-policy 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.

rules/baseline-policy.mdc · 74 lines

What it actually says

Baseline Policy (CodeCortexLoop v2.1)

Purpose

Legacy codebases may have hundreds of pre-existing findings. Baseline mode lets teams adopt CodeCortexLoop without blocking every PR on old debt.

Fingerprint

Each finding gets a stable fingerprint:

hash(category + location_with_line + full_normalized_problem)
  • Location includes line numbers (file paths normalized to forward slashes)
  • Problem normalized: lowercase, whitespace collapsed, full text (not truncated)

Same issue at same place = same fingerprint across runs.

Buckets

Bucket Definition
new In current report, not in baseline
fixed In baseline, not in current open findings
remaining In both — accepted technical debt

Accept baseline

Run once (or when intentionally accepting new debt):

node scripts/baseline.mjs accept docs/cortexloop/report.json

Stores .cortexloop/baseline.json. Commit this file to the repo so CI shares the same baseline.

Diff

Every PR / run after baseline exists:

node scripts/baseline.mjs diff docs/cortexloop/report.json

Produces .cortexloop/baseline-diff.json.

CI gate with --baseline

node scripts/ci-gate.mjs docs/cortexloop/report.json --baseline

Counts only new findings for Critical/High exit codes. Remaining baseline debt does not fail CI.

When to re-accept

  • Team deliberately accepts additional debt (discuss in PR)
  • Fingerprint churn from mass renames (rare — prefer fixing root cause)
  • Major refactor changes finding locations en masse

Re-accept only with explicit user confirmation.

Agent behavior

  • Never auto-accept baseline in Direct mode
  • Present new/fixed/remaining counts in summary
  • Highlight new Critical/High prominently
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 · 74 lines · 15 tokens per session scan A 4f84ba2826e4

Subscribe to this mod's changes

baseline-policy is a cursor rule published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 439 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.