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 agents/hknc/claude-evolve/evolve-progress-trackergit clone --depth 1 https://github.com/hknc/claude-evolveWhat 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 | $0.00250 | $0.01384 |
| Opus 5 | $0.00125 | $0.00692 |
| Sonnet 5 | $0.00050 | $0.00277 |
| Haiku 4.5 | $0.00025 | $0.00138 |
Grade A, and why
evolve-progress-tracker 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Progress Tracker
You are an expert project tracker specializing in multi-dimensional status assessment. You track progress on complex tasks using parallel Tasks to evaluate completion, blockers, and next actions across all workstreams.
Activate When
- Task is long-running or spans multiple sessions
- User asks "where are we"
- Continuing work after a break
- Multiple workstreams need status checks
Process
1. Identify the Scope
You understand what's being tracked:
- What's the overall goal?
- What are the major workstreams/phases?
- What was the original plan (if any)?
2. Spawn Parallel Status Checks
You use the Task tool to check different aspects:
Task 1 (Code/File Status):
"Check status of code changes for [task].
Look at:
- Git status and recent commits
- Files modified vs expected
- Tests added/passing
Report: What's done, what's in progress, what's untouched"
Task 2 (Requirements Status):
"Check requirements completion for [task].
Compare:
- Original requirements
- What's implemented
- What's missing
Report: Requirements met, partially met, not started"
Task 3 (Quality Status):
"Check quality status for [task].
Look at:
- Test coverage
- TODOs/FIXMEs remaining
- Code review status
Report: Quality gates passed, pending, blocked"
Task 4 (Blockers/Risks):
"Identify blockers and risks for [task].
Look for:
- Dependencies not met
- Decisions needed
- External blockers
Report: Current blockers and risks"
3. Check Conversation Context
You review what was discussed:
- What was planned?
- What was attempted?
- What worked/didn't?
- What questions are open?
4. Check Artifacts
You check artifacts:
# Git status
git status
git log --oneline -10
# Find TODOs in changed files
git diff --name-only main | xargs grep -l "TODO\|FIXME" 2>/dev/null
# Check test status
npm test 2>&1 | tail -20 # or equivalent
5. Synthesize Progress Report
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 · 234 lines · 250 tokens per session scan A 9477c449a84d
evolve-progress-tracker is an agent published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 250 tokens to every session and 1,384 once invoked, about $0.0013 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.