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 skills/pyros-projects/limitless/memory-promotenpx skills add pyros-projects/limitless --skill memory-promotegit clone --depth 1 https://github.com/pyros-projects/limitlessWrote 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/skills/pyros-projects/limitless/memory-promote)<a href="https://agentmods.dev/skills/pyros-projects/limitless/memory-promote"><img src="https://agentmods.dev/badge/skills/pyros-projects/limitless/memory-promote.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 | $0.00078 | $0.00506 |
| Opus 5 | $0.00039 | $0.00253 |
| Sonnet 5 | $0.00016 | $0.00101 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
memory-promote 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 4d 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.
What it actually says
Memory Promote
BETA — This memory system is in active testing. If you encounter bugs, confusing behavior, or have suggestions, run:
codies-memory feedback "describe what happened"— your feedback is saved and reviewed.
When To Use
- At session close (automatic evaluation)
- When an operator explicitly requests promotion
- When promotion thresholds are met during work
Promotion Paths
Within Project
inbox -> thread (recurring topic)
inbox -> lesson (actionable pattern)
thread -> decision (confirmed across 2+ sessions)
thread -> lesson (reusable pattern)
decision -> lesson (reusable pattern)
Project to Global
project lesson -> global lesson (proven across 2+ projects)
How To Run
# List active inbox items for promotion review
codies-memory list inbox --status active
# Evaluate all inbox items for promotion (no CLI equivalent yet)
uv run python -c "
from pathlib import Path
from codies_memory.records import list_records
from codies_memory.promotion import evaluate_for_promotion
vault = Path('.memory')
inbox_items = list_records(vault, 'inbox', scope='project')
for item in inbox_items:
result = evaluate_for_promotion(item, context={'session_count': 3})
if result['eligible']:
print(f' Promote: {item[\"frontmatter\"][\"title\"][:60]}')
print(f' Suggested: {result[\"suggested_types\"]}')
"
# Promote an inbox item to a thread
codies-memory promote /path/to/record.md --to thread
# Promote a project lesson to global
codies-memory promote /path/to/lesson.md --to-global
Probation
All promoted records enter a 7-day probation window. During probation:
- Contradictory evidence can demote the record back
- Stronger newer records can supersede it
- The record participates in boot and retrieval normally
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.
- 4d ago First seen · 69 lines · 78 tokens per session scan A 7c5d5e96a72e
memory-promote is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 21d ago), licensed MIT. It adds 78 tokens to every session and 506 once invoked, about $0.0004 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 skills, from other repositories
dag-recall
Walks the memory DAG to recall detailed context on demand — query, expand, and assemble cited answers from hierarchical summaries without re-reading raw transcripts.
memory-dag-compactor
Builds hierarchical summary DAGs from MEMORY.md with depth-aware prompts — leaf summaries preserve detail, higher depths condense to durable arcs, preventing information loss during compaction.
memory-graph-builder
Parses OpenClaw's flat MEMORY.md into a structured knowledge graph — detects duplicates, contradictions, and stale entries, then builds a compressed memory digest optimized for system prompt injection.
compaction-resilience-guard
Monitors memory compaction for failures and enforces a three-level fallback chain — normal, aggressive, deterministic truncation — ensuring compaction always makes forward progress.
context-assembly-scorer
Scores how well the current context represents the full conversation — detects information blind spots, stale summaries, and coverage gaps that cause the agent to forget critical details.
large-file-interceptor
Detects oversized files that would blow the context window, generates structural exploration summaries, and stores compact references — preventing a single paste from consuming the entire budget.