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 timharris707/skills --skill domain-memorygit clone --depth 1 https://github.com/timharris707/skillsWrote 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/timharris707/skills/domain-memory)<a href="https://agentmods.dev/skills/timharris707/skills/domain-memory"><img src="https://agentmods.dev/badge/skills/timharris707/skills/domain-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/skills/timharris707/skills/domain-memory"><img src="https://agentmods.dev/badge/skills/timharris707/skills/domain-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 | $0.00064 | $0.02188 |
| Opus 5.5 | $0.00026 | $0.00875 |
| Sonnet 5.5 | $0.00013 | $0.00438 |
| Haiku 4.5 | $0.00006 | $0.00219 |
Grade A, and why
domain-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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain memory
Read the Codex desktop binding when this workflow needs harness mechanics, model routing, or recovery.
Per-repo institutional memory: what the repo's words mean, and why its settled decisions went the way they did. It is written as side effects of work, never as a documentation chore. router and setup orient a session on the pack and the repo's bindings; this skill is the third orientation instrument beside them, and it orients the session on the domain.
This skill is the portable protocol: two artifacts in one store, the write and read moments that keep it alive, and evolution rules that keep it honest. Where the store lives, when consolidation is offered, and whether backfill runs are binding slots the team-workflow setup interview fills.
Read the team-workflow binding doc first; its domain-memory section names the memory home.
1. One store, two artifacts
- The glossary: one small, opinionated file of domain terms, each entry a canonical term, a tight definition, and the synonyms to avoid (the rules live in references/formats.md). It updates in place: a term means one thing now, and the file says what.
- Decision records: one small file per settled decision, title, date, the decision, the load-bearing reason, and links to the ticket or PR that carried it. A record costs under a minute to write, in plain English a non-engineer decider reads without translation. The reason is the record's value: a future session needs to know why, so it can tell new evidence from re-litigation.
Formats for both live in references/formats.md. Files are created lazily: the glossary when the first term settles, the decisions directory when the first record lands; an empty store on day one is the correct starting state.
The store is repo files at the memory home the binding names: a decisions directory plus a terms file (e.g. docs/decisions/ + docs/terms.md). The tracker holds work in flight; the repo carries the durable why: a decision's record outlives the ticket that produced it. And it is one store: in repos also bound to codebase-review, that skill's rejection-memory slot points at this memory home, so rejected candidates are decision records here, never a second store.
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.
- 11d ago Changed c0c79414a29a
- 28d ago First seen · 76 lines · 64 tokens per session scan A 6d9fb63ef61b
domain-memory is a skill published in the GitHub repository timharris707/skills (41 stars, last pushed 7d ago), licensed MIT. It adds 64 tokens to every session and 2,188 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
g-resume
Re-hydrate a fresh session with the right slice of the durable record. The read-side counterpart to /g-retro — selectively retrieves the relevant retro, ADRs, journal, and handoff keyed by the current branch/milestone/first-task, and assembles a focused re-entry briefing. Loads distilled context into a clean window…
knowledge-audit
Knowledge base health audit. Scans knowledge docs, analyzes content composition, detects stale references, tiny/oversized files, three-criteria compliance, outputs health report and optimization suggestions.
handoff
Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work…
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…