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 roarista/awesome-harness --skill recallgit clone --depth 1 https://github.com/roarista/awesome-harnessWrote 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/roarista/awesome-harness/recall)<a href="https://agentmods.dev/skills/roarista/awesome-harness/recall"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/recall/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/roarista/awesome-harness/recall"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/recall.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 | $0.00082 | $0.00629 |
| Opus 5 | $0.00041 | $0.00315 |
| Sonnet 5 | $0.00016 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
recall 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 9d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recall — fast memory retrieval
Step 1 of THE PROCEDURE (
~/.codex/AGENTS.md). Two stores, two CLIs, both plain command-line tools a Codex session can run directly.
Global memory — memgraph
python3 ~/.claude/tools/memgraph/mem.py query "<topic>" [-k N] # full-text search, ranked — your main verb
python3 ~/.claude/tools/memgraph/mem.py graph <name> # a record's neighbors (links, supersedes)
python3 ~/.claude/tools/memgraph/mem.py list [--type user|feedback|project|reference]
python3 ~/.claude/tools/memgraph/mem.py rebuild # refresh the index after memory files change
The index lives next to the script (~/.claude/tools/memgraph/out/), which is why the path points there even from a Codex session — there is one index, shared. If out/memindex.sqlite is missing, run python3 ~/.claude/tools/memgraph/build.py first.
Flow: query → read the top hit's name/description/path → Read the file only if the record is load-bearing → optionally graph <name> to pull the one linked record you need.
Per-repo memory — mulch
In a repo with .mulch/:
ml prime # load the repo's records at the start of substantive work
ml search "<topic>" # targeted lookup
ml is at ~/.npm-global/bin/ml. If it is not on PATH, call it by that full path.
Session ritual
- Before planning substantive work: query the task's topic in both stores. Load the specific decisions and failure modes that apply.
- Before proposing something new: query it first — avoid re-deciding what is already recorded, and avoid building what already exists.
- At the close: if a durable lesson emerged, record it (
compact-prepstep 2), thenmem.py rebuildif you wrote a global memory file.
Guardrails
- Read budget: ≤5 file reads per recall. Hop card-by-card (
query→ top hit → onegraphhop). If 5 reads have not answered it, narrow the query rather than widening the reads. - Retrieval is read-only. Never mutate a memory record as a side effect of a query.
- Dangling
[[name]]links are expected — they mark a not-yet-written record, signal rather than error.
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.
- 9d ago First seen · 45 lines · 82 tokens per session scan A 06eefa51ba64
recall is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 13d ago), licensed MIT. It adds 82 tokens to every session and 629 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.