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 skills add rjmurillo/ai-agents --skill memory-enhancementgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/memory-enhancement)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/memory-enhancement"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/memory-enhancement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/memory-enhancement"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/memory-enhancement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 291 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 240 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00080 | $0.03022 |
| Opus 5 | $0.00040 | $0.01511 |
| Sonnet 5 | $0.00016 | $0.00604 |
| Haiku 4.5 | $0.00008 | $0.00302 |
Grade A, and why
memory-enhancement 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 5d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Enhancement
Manage citations, verify code references, and track confidence scores for Serena memories. Ensures memories stay accurate by linking them to specific code locations and detecting when those locations change.
Triggers
add citation to memory- Link memory to specific code locationverify memory citations- Check if code references are still validcheck memory health- Generate staleness report across all memoriesupdate memory confidence- Recalculate trust score based on verification
Quick Reference
| Input | Output | Duration |
|---|---|---|
| Memory ID + code reference | Citation added with validation | < 5 seconds |
| Memory directory | Health report with stale memories | < 30 seconds |
| Verification results | Updated confidence scores | < 10 seconds |
Decision Tree
Need memory enhancement?
│
├─ Add citation to memory → edit the memory file (no CLI command)
├─ Verify citations → verify or verify-all command
├─ Check memory health → health command
├─ Traverse memory graph → graph command
└─ Show confidence scores → confidence command
Command Surface
Global options come before the subcommand. Placing --repo-root or
--memories-dir after the subcommand exits 2.
python -m memory_enhancement [--repo-root PATH] [--memories-dir PATH] <command>
| Command | Options | Exit codes |
|---|---|---|
verify |
--memory-id ID |
1 if any citation is invalid, or the id is unknown |
verify-all |
--json |
1 if any citation is invalid |
health |
--json, --text, --markdown (default) |
1 if any citation is broken or stale, or any memory is stale |
graph |
--start ID (required), --depth N |
1 if the start id is unknown |
confidence |
none | 0 |
search |
QUERY (positional), --top N, --json |
0 |
--memories-dir must resolve inside --repo-root; otherwise the CLI exits 1.
A memory id is its path under the memories directory without the .md
suffix, so .serena/memories/testing/foo.md has the id testing/foo.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 323 lines · 80 tokens per session scan A 719d99679c43
memory-enhancement is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 3,022 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 2026-09-03.
Other skills, from other repositories
context-recovery
Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recover prior work. Use for requests such as "where were we before compaction?" when the current thread is insufficient. Do not trigger on a generic "continue" when the current thread already provides an…
ci-cd
A guide for designing automated build and delivery workflows with GitHub Actions. These workflows can run checks such as tests, code-quality scans, coverage checks, and builds when code is pushed or a pull request is opened.
context-search
A continuity workflow for finding context from earlier coding-agent sessions. It can inspect continuation notes and session records when a task refers to previous work.
abmind-runtime-operations
Inspect and maintain abmind memory, persona files, sleep, backups, encryption, and runtime health.
memory-search
Search persistent memory for facts, decisions, and past conversations.
topic-save
Save and manage topic-specific knowledge files from conversations.