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.
git clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/update-memory)<a href="https://agentmods.dev/commands/manishiitg/coding-agent-loop/update-memory"><img src="https://agentmods.dev/badge/commands/manishiitg/coding-agent-loop/update-memory/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/commands/manishiitg/coding-agent-loop/update-memory"><img src="https://agentmods.dev/badge/commands/manishiitg/coding-agent-loop/update-memory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00391 |
| Opus 5.5 | $0.00000 | $0.00156 |
| Sonnet 5.5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
update-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 25d 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
Review this conversation and persist what is worth keeping as durable project knowledge — both memory and skills.
{{context}}
Memory
- Read the project-root MEMORY.md first (create it if it does not exist).
- Extract stable, verified project truths from this conversation: facts, preferences, decisions, constraints, and corrections. Test each candidate with "Crew should remember that…".
- Follow the project memory contract: concise reverse-chronological entries, one topic per dated heading, merge into an existing topic instead of appending a duplicate, and replace or remove entries that newer evidence contradicts.
- Do not save guesses, transient status, raw chat, credentials, or unverified research.
Skills
Invoking this command is my explicit ask to preserve reusable procedures, so the normal "skills change only on explicit ask" bar is met for what follows:
- Call
list_skillsfirst and inspect the names and descriptions of every existing project skill before choosing a destination. - For each genuinely reusable procedure in this conversation — test it with "When asked to do X, Crew should…" — create or update a focused project-local skill at
skills/<skill-name>/SKILL.mdwith concisenameanddescriptionfrontmatter. Never write it into the account-wideskills/custom/library. - Update an existing skill only when the new knowledge has the same topic and would be loaded for the same kind of future request; create a separate, clearly named skill when the topic, trigger, or outcome differs. If an existing skill has become a catch-all, split the relevant material into focused skills. Link memory and skill entries rather than duplicating instructions.
- Select each created or updated skill for this project with
update_project_skill_selectionso the runtime can load it.
Report
Tell me briefly what you added or changed in MEMORY.md and in skills — and what you deliberately left out, so I can correct you.
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.
- 25d ago First seen · 24 lines · 0 tokens per session scan A 3ade97d7f430
update-memory is a command published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 391 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 2026-09-22.
Other commands, from other repositories
blackboard
Read or write a Network-AI blackboard key (shared multi-agent state).
go
You MUST start your FIRST response with this exact agent activation line.
dashboard-session-fork
Fork a session into a new one. Usage /dashboard:session-fork.
dashboard-session-hide
Hide a session from the dashboard list. Usage /dashboard:session-hide.
resolve-dependabot-prs
Triage open Dependabot PRs, return a quick risk/action summary table, then enter planning mode with an ordered rebase→merge→follow-up→resume resolution plan.
relay
Create or update a root relay.md session-continuation document.