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 rules/jketreno/clare/clare-workflowgit clone --depth 1 https://github.com/jketreno/clareWrote 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/rules/jketreno/clare/clare-workflow)<a href="https://agentmods.dev/rules/jketreno/clare/clare-workflow"><img src="https://agentmods.dev/badge/rules/jketreno/clare/clare-workflow.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 | $0.00750 | $0.00750 |
| Opus 5 | $0.00375 | $0.00375 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
clare-workflow 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLARE Workflow
This project uses the CLARE framework. Apply these rules to every coding task.
Session Start — Announce Active Principles
At the start of the first response in any new Composer session or conversation, read clare/autonomy.yml and output this status block before answering:
🔒 CLARE framework active
C · Constrained — verify-ci.sh enforced
L · Limited — autonomy.yml: [found ✅ | NOT FOUND ⚠]
A · Assertive — constraint tests required
R · Reality-Aligned — sources_of_truth: [N concepts | none declared]
E · Ephemeral — generated files protected
humans-only zones: [list paths, or "none"]
verify-ci.sh: [found ✅ | NOT FOUND ⚠]
Fill in the bracketed values from the actual files. Show this block once per session. If clare/autonomy.yml is missing, tell the user to run the CLARE installer.
Before Starting Any Task
- Read
clare/autonomy.ymlto identify autonomy levels for affected paths - Read
clare/principles.mdfor applicable constraints - For complex tasks (3+ files, new patterns): use PLAN mode first — show the plan, wait for approval, then implement
Verify After Code Changes
When to run it: only in a turn where you created, updated, or deleted a file. If you edited no files this turn — including any plan-mode, research, or read-only turn — do not run it.
How to run it (a terminating sequence, not a loop):
- Run
./clare/verify-ci.shonce. - Exit code 0 → report PASS and stop.
- Non-zero → fix the reported failures, then run it once more.
Do not invoke it again for any other reason.
Reporting: if you ran verify-ci.sh this turn, include:
- verify-ci.sh result: PASS/FAIL
- command used
- whether
--fast,--fix, or--fail-fastwas used (if applicable)
If you edited no files this turn, state "no edits this turn — verify-ci.sh not run" and do not invoke it. If running in read-only mode (Ask mode), state: "verify-ci.sh not run because session is read-only."
Rules guide behavior; CI enforces it. ./clare/verify-ci.sh remains the source of truth.
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.
- 3d ago First seen · 82 lines · 750 tokens per session scan A 51953ae9c7ee
clare-workflow is a cursor rule published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 750 tokens to every session, about $0.0037 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.