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/thinkinaixyz/deepchat/memory-managementnpx skills add ThinkInAIXYZ/deepchat --skill memory-managementgit clone --depth 1 https://github.com/ThinkInAIXYZ/deepchatWrote 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/thinkinaixyz/deepchat/memory-management)<a href="https://agentmods.dev/skills/thinkinaixyz/deepchat/memory-management"><img src="https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/memory-management.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 | $0.00026 | $0.00667 |
| Opus 5 | $0.00013 | $0.00333 |
| Sonnet 5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
memory-management 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Management
Use this skill when a task may produce durable learning or when the user asks you to recall, remember, continue earlier work, preserve an exact statement, capture a reusable procedure, or handle a recurring need.
Recall
Rely on automatic memory injection for ordinary context. Use memory_recall when the user refers to previous work with cues such as again, last time, before, continue, same project, remember, or asks what you already know.
Use tape_search and then tape_context when the user needs source evidence, exact wording, logs, command output, file snippets, or why a prior decision was made. Memory is a durable conclusion layer, not the raw transcript.
Remember
Use memory_remember only for durable conclusions that should change future behavior. Choose the most specific category:
user_preference: stable user preferences, constraints, communication style, environment choices.project_fact: durable project conventions, architecture entry points, commands, dependencies, paths, or operational constraints.task_outcome: completed, blocked, or deliberately deferred task results. Include status, outcome, and blocker in prose when relevant.heuristic: reusable troubleshooting strategy, workflow, decision rule, or engineering lesson.anti_pattern: repeated mistake, unsafe approach, brittle pattern, stale assumption, or thing to avoid.
Do not remember raw tool results, bash output, grep output, file contents, transient mechanics, one-off failures, secrets, credentials, hidden reasoning, or anything only useful for the current turn.
Verbatim Scope
Store exact wording only when the user explicitly asks you to remember a sentence or phrase verbatim. In that case, keep the requested text intact and make the surrounding content minimal.
Automatic extraction is different: it should normalize durable facts into concise memory content, deduplicate related entries, and avoid preserving raw transcript text.
Procedures -> Skill
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 · 56 lines · 26 tokens per session scan A 95d2bbc22e05
memory-management is a skill published in the GitHub repository ThinkInAIXYZ/deepchat (6,302 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 667 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 skills, from other repositories
audit-i18n
Audit localization / i18n coverage across the compose-resources surface (9 modules x 9 locales). Finds strings that exist in English but not in some or all languages, keys left as untranslated English stubs inside a translated file, stale keys the base dropped, and English literals that never reached a strings.xml at…
sync-upstream
Sync the Switchboard client with a newer official LibreChat server version — a stable release, a release candidate, or a PARTIAL sync up to an untagged upstream commit (e.g. current dev HEAD). If the client is ALREADY at the target commit, runs an AUDIT of the last synced delta to catch anything that was missed.…
audit-deps
Audit open dependabot PRs in this repo. Spawns one investigator per PR (each with a codebase-walk sub-agent), produces a comparison table with per-PR risk + recommendation, and proposes a merge order that minimizes rebase churn. Audit-only — stops at recommendations; user authorizes execution. Use when dependabot has…
release-highlights
Add a hand-written Highlights section to a GitHub release whose notes were auto-generated, summarizing the release's PRs in user-facing language above the generated changelog. Reads every PR in the range, drafts the section in the repo's house style, asks about ambiguous wording, and writes only after approval. Use…
update-web-assets
Update the third-party JavaScript vendored into the app for the artifact, diagram, and math WebViews (KaTeX, mermaid, marked, highlight.js, Tailwind, Babel, React). Checks what is outdated, reads each pin's rationale before proposing a bump, re-downloads from the official source, verifies the lock, and runs the gates.…
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.