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/agricidaniel/ace-claude-code/consider-issuesgit clone --depth 1 https://github.com/AgriciDaniel/ace-claude-codeWhat 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 | $0.00012 | $0.02056 |
| Opus 5 | $0.00006 | $0.01028 |
| Sonnet 5 | $0.00002 | $0.00411 |
| Haiku 4.5 | $0.00001 | $0.00206 |
Grade A, and why
ace:consider-issues 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<issues_md_format>
Understanding ISSUES.md
Origin
ISSUES.md is created and updated during plan execution when agents encounter situations that deviate from the plan. This happens when:
- A task cannot be completed as specified
- An agent discovers a problem outside their current task scope
- Edge cases are found that weren't anticipated
- Technical debt is identified during implementation
- Enhancement opportunities are spotted but out of scope
Agents log issues using the log-issue command, which appends to ISSUES.md.
File Structure
# Deferred Issues
**Last Updated:** [timestamp]
**Total Issues:** [N]
---
## ISS-001: [Title]
- **Type:** Enhancement | Bug | Tech Debt | Missing Feature | Optimization
- **Priority:** Critical | High | Medium | Low
- **Effort:** Small (< 1 hour) | Medium (1-4 hours) | Large (> 4 hours)
- **Source:** [Phase X, Plan Y, Task Z] or [Agent: ALPHA/BETA/GAMMA]
- **Logged:** [timestamp]
- **Description:**
[Detailed description of the issue]
- **Context:**
[Where this was discovered, what was being worked on]
- **Suggested Approach:**
[Optional: How the discovering agent suggests fixing it]
- **Affected Files:**
- [file1.ts]
- [file2.ts]
---
## ISS-002: [Title]
...
Each issue is separated by --- and contains structured metadata for categorization.
</issues_md_format>
1. Load and Parse Issues
Read ISSUES.md and extract all issue entries. For each issue, capture:
- ID and title
- Type, priority, and effort estimates
- Source (which phase/plan/task created it)
- Age (how long it's been deferred)
Build an in-memory index of all issues for categorization.
2. Categorize Issues
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 · 287 lines · 12 tokens per session scan A d099a535241a
ace:consider-issues is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 2,056 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
canvas
AI-orchestrated visual canvas production — create, populate, layout, present, generate, and export Obsidian canvases.
document
Generate documentation for code.
review
Review code for best practices and issues.
test
Generate comprehensive tests for a file or function.
fix-issue
Analyze and fix a GitHub issue.
migrate
Create migration plan for upgrade.