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/adilkalam/orca/project-memorygit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00033 | $0.01757 |
| Opus 5 | $0.00016 | $0.00879 |
| Sonnet 5 | $0.00007 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
project-memory 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Memory Management
Parse the user's command to determine which action to take:
Command: /project-memory $ARGUMENTS
Subcommand Routing
Based on the arguments, execute ONE of the following:
1. Status (default, no args, or status)
Trigger: /project-memory or /project-memory status
Show memory system status:
echo ""
echo " Project Memory Status"
echo ""
echo ""
# Workshop status
if [ -f ".claude/memory/workshop.db" ]; then
echo "Workshop: .claude/memory/workshop.db"
workshop --workspace .claude/memory info 2>/dev/null || echo " (run 'workshop info' for details)"
else
echo "Workshop: Not initialized"
fi
echo ""
# code-index.db status
if [ -f ".claude/memory/code-index.db" ]; then
echo "code-index.db: .claude/memory/code-index.db"
python3 ~/.claude/scripts/code-index.py status 2>/dev/null || echo " (run 'code-index.py status' for details)"
else
echo "code-index.db: Not initialized"
fi
echo ""
# Recent activity
echo ""
echo "Recent Activity:"
workshop --workspace .claude/memory recent --limit 5 2>/dev/null || echo " (no recent activity)"
2. Initialize (init or --initialize)
Trigger: /project-memory init or /project-memory --initialize
Initialize the memory workspace:
mkdir -p .claude/memory
workshop --workspace .claude/memory init
This will:
- Create
.claude/memory/directory structure - Initialize Workshop database (workshop.db)
3. Why Query (why <topic>)
Trigger: /project-memory why <topic>
Query past decisions about a topic:
workshop --workspace .claude/memory why "<topic>"
Display the results clearly. If no results, suggest recording a decision.
4. Record Decision (decide <text> or decision <text>)
Trigger: /project-memory decide <text> or /project-memory decision <text>
Record a decision. Ask the user for reasoning if not provided:
- If text contains
-ror--reason, parse it:workshop --workspace .claude/memory decision "<decision_text>" -r "<reasoning>"
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 · 269 lines · 33 tokens per session scan A 6aa9cd30a4b3
project-memory is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,757 once invoked, about $0.0002 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
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.