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/benshapyro/cadre-devkit-claude/progressgit clone --depth 1 https://github.com/benshapyro/cadre-devkit-claudeWhat 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 | $0.00007 | $0.01402 |
| Opus 5 | $0.00003 | $0.00701 |
| Sonnet 5 | $0.00001 | $0.00280 |
| Haiku 4.5 | $0.00001 | $0.00140 |
Grade A, and why
progress 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Progress Command
Compress learned knowledge into reusable documents for future sessions.
Purpose
After deep exploration or research, save findings so future sessions don't need to re-learn the same things. Creates "cheat sheets" for your codebase.
When to Use
- After
/researchsessions with valuable findings - After exploring a complex part of the codebase
- When you've learned something that will be useful again
- When starting work in a new area of the codebase
File Naming Convention
Format: YYYY-MM-DD-NNN-description.md
YYYY-MM-DD- Today's date (use actual current date)NNN- Sequential number for the day (001, 002, etc.)description- Short kebab-case description of topic
Examples:
2025-12-03-001-authentication-system.md2025-12-03-002-payment-processing.md2025-12-04-001-api-rate-limiting.md
To determine next number:
- List existing files in
docs/for today's date - Find highest NNN for today
- Increment by 1 (or start at 001 if first of day)
Workflow
1. Identify What Was Learned
Review the current conversation for:
- Files and entry points discovered
- Patterns and conventions identified
- Gotchas and edge cases found
- Key relationships between components
- External documentation links
2. Propose Knowledge Document
Output Format:
## Proposed Knowledge Document
**Topic:** [topic name]
**File:** `docs/YYYY-MM-DD-NNN-description.md`
### Preview
# [Topic] - Quick Reference
**Date:** YYYY-MM-DD
**Context:** [What prompted this research]
**Key Files:**
- `path/to/main/file.ts:line` - [description]
- `path/to/related/file.ts` - [description]
**Entry Points:**
- [Where to start for common tasks]
**Key Patterns:**
- [Pattern 1]
- [Pattern 2]
**Gotchas:**
- [Common mistake or edge case]
**Related Docs:**
- [Link to external docs]
---
Save this document? (yes / edit first / cancel)
3. Await Approval
Wait for user to:
- Approve - Create the file
- Edit - User provides changes, then save
- Cancel - Don't save
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.
- 2d ago First seen · 229 lines · 7 tokens per session scan A fe7d0b72976b
progress is a command published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 8mo ago), licensed MIT. It adds 7 tokens to every session and 1,402 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.