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/samibs/skillfoundry/recallgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/recall)<a href="https://agentmods.dev/commands/samibs/skillfoundry/recall"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/recall.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 | $0.00000 | $0.01139 |
| Opus 5 | $0.00000 | $0.00570 |
| Sonnet 5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
recall 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/recall — Layered Knowledge Recall
Progressive disclosure search across the memory bank. Three modes: index, preview, full.
Usage
/recall "query" Search and show compact index
/recall "query" --type=decision Filter by entry type
/recall "query" --min-weight=0.7 Filter by minimum weight
/recall "query" --since=7d Filter by recency
/recall "query" --tags=auth,security Filter by tags
/recall --preview id1,id2,id3 Show content summaries for specific entries
/recall --full id1,id2 Show complete entries with all fields
How It Works
Step 1: Index Mode (default)
When you run /recall "query", search all memory_bank/knowledge/*.jsonl files and return a compact index:
| ID | Type | Score | Weight | Content |
|---|---|---|---|---|
| abcdef12 | decision | 130 | 0.9 | "Standalone agentic loop with zero React deps..." |
| 12345678 | fact | 85 | 0.7 | "Pipeline engine is 6-phase: IGNITE→PLAN→FORGE..." |
Scoring (matches semantic-search.sh algorithm):
- Exact phrase match: +100
- Individual word match (>2 chars): +10 per word
- Type field match: +20
- Weight bonus: +10 * weight
- Tags match: +5 per word
Filters (combinable):
--type=decision|fact|error|preference|pattern--min-weight=0.7(0.0 to 1.0)--since=7d|30d|4w|2026-03-01--tags=auth,security(match any)--limit=10(default: 20)
Max 20 results. Total output: ~400 tokens.
Step 2: Preview Mode
After seeing the index, selectively expand entries:
/recall --preview abcdef12,12345678
Returns first 200 chars of content + metadata (type, weight, tags, created date). Total output: ~600 tokens.
Step 3: Full Mode
For entries you need complete detail:
/recall --full abcdef12
Returns complete canonical entry with all fields (content, tags, weight, lineage, reality_anchor, context).
Implementation
The search engine is sf_cli/src/core/layered-recall.ts with three functions:
recallIndex(query, workDir, filters)— compact search resultsrecallPreview(ids, workDir)— content summariesrecallFull(ids, workDir)— complete entries
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 · 96 lines · 0 tokens per session scan A 1ded09a74d1d
recall is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,139 tokens. 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 2026-09-03.
Other commands, from other repositories
generate-project-context
Create project-context.md with AI rules. Use when the user says ""generate project context"" or ""create project context"".
checkpoint
Checkpoint — Persistent Memory Archival.
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.
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.