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/whitequeen306/code-cortex-loop/cortexloop-baselinegit clone --depth 1 https://github.com/whitequeen306/code-cortex-loopWhat 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 | $0.00016 | $0.00451 |
| Opus 5 | $0.00008 | $0.00226 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
cortexloop-baseline 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 yesterday.
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.
What it actually says
/cortexloop-baseline
Manage technical debt baseline so CodeCortexLoop only fails on new findings in CI.
When to use
- First time on a legacy repo — too many existing issues? Run accept to snapshot current debt.
- Every PR after that — run diff; CI gates only on new Critical/High findings.
Flow
1. Run analysis first
Run /cortexloop or /cortexloop-pre-pr in Report or CI mode to produce docs/cortexloop/report.json.
2. Choose action
Ask the user:
- Accept baseline — snapshot all current open findings as accepted debt
- Diff against baseline — compare current report to baseline, show new/fixed/remaining
3. Execute scripts
From project root:
Accept (first time):
node scripts/baseline.mjs accept docs/cortexloop/report.json
Diff (subsequent runs):
node scripts/baseline.mjs diff docs/cortexloop/report.json
Outputs:
.cortexloop/baseline.json— accepted fingerprints.cortexloop/baseline-diff.json— new / fixed / remaining
4. CI with baseline
node scripts/baseline.mjs diff docs/cortexloop/report.json
node scripts/ci-gate.mjs docs/cortexloop/report.json --baseline
Only new Critical/High findings fail the gate. Remaining baseline debt is ignored.
Rules
Load rules/baseline-policy.mdc for fingerprint semantics and ratchet behavior.
Report summary
After diff, summarize for the user:
| Bucket | Meaning |
|---|---|
| new | Introduced since baseline — must fix or update baseline |
| fixed | Was in baseline, no longer present — progress! |
| remaining | Still open from baseline — tracked debt |
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.
- yesterday First seen · 68 lines · 16 tokens per session scan A 85f6a266e625
cortexloop-baseline is a command published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 451 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.