Borrowing it
Nothing to install: this file belongs to samzong/Recall. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/samzong/Recall/main/.agents/skills/recall-ext/SKILL.mdgit clone --depth 1 https://github.com/samzong/RecallWrote 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/samzong/recall/recall-ext)<a href="https://agentmods.dev/skills/samzong/recall/recall-ext"><img src="https://agentmods.dev/badge/skills/samzong/recall/recall-ext/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/samzong/recall/recall-ext"><img src="https://agentmods.dev/badge/skills/samzong/recall/recall-ext.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00504 |
| Opus 5.5 | $0.00012 | $0.00202 |
| Sonnet 5.5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
recall-ext 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall Ext
Read extensions/AGENTS.md and docs/extensions.md for the extension boundary,
CLI protocol, and managed-install contract. Compare implementation with the
contract; resolve disagreements before changing behavior.
Develop
- Use
extensions/recall-probe/for the minimal package layout. Add the newrecall-<name>binary to workspace members and keep its version independent of core. - Implement
--recall-extension-manifestwithname, packageversion,protocol, andmin_recall. Choose compatibility values from the CLI features actually consumed; do not copy the probe's legacy values orcommandsfield into a new extension. - Pass an explicit
--projecton scoped Recall queries and syncs; useallonly for global work. Omitted scope follows the caller's working directory. recall session show --format jsonreturns metadata by default. Request--messagesor--include metadata,messageswhen reading transcripts.- For host changes, trace
src/extension.rsagainst the managed-install contract: official catalog, checksum and manifest validation, managed-only dispatch and removal. Do not add PATH discovery or a third-party registry.
Verify
Run the relevant package checks and exercise its CLI protocol:
cargo build -p recall-<name>
cargo test -p recall-<name>
cargo run -p recall-<name> -- --recall-extension-manifest
For host changes, run cargo test --lib extension::tests; for catalog changes,
check cargo run -- ext list --available. Run root make check before ship.
Release
Bump the package version only when a release is requested. Follow
.github/workflows/extension-release.yml for version/tag validation, target
packaging, publication, and catalog generation. Extension tags are
recall-<name>-v<version>; a core tag does not release an extension.
Verify the affected target archives, manifests, and SHA-256 checksums using
that workflow. Never hand-edit website/public/extensions/catalog.json or
couple extension and core releases unless protocol compatibility requires it.
What ships with it
1 file 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.
- 1mo ago Changed · -60 lines · -29 tokens per session 974d1c18e7fc
- 1mo ago First seen · 112 lines · 60 tokens per session scan A 4f7a1763a1ff
recall-ext is a skill published in the GitHub repository samzong/Recall (107 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 504 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
solon-development-skill
Solon Java framework expert (NOT Spring). Use ONLY for projects already using or being newly built with the Solon framework. DO NOT USE for projects the user is keeping on Spring/Spring Boot — if the workspace is a Spring project (spring-boot-starter-, @SpringBootApplication, application.yml) and the user has not…
orbit
Orbit — the task/audit/dispatch layer for AI coding agents. Use for anything touching a task ID, .orbit/, orbit CLI or orbit. MCP tools, the docs corpus, friction records, jobs and jrun- runs, routines, auto-tasks, the sweep clock, worktree GC, the dashboard, or setting Orbit up on a machine or repository. Covers both…
simplicio-autoresearch
Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's autoresearch pattern (and the ECC autoresearch-agent) with mandatory yool guardrails (§11…
simplicio-orient
Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their…
simplicio-learn
Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from…
simplicio-review
Deep, adversarial branch review — parallel subagents on separate rubrics (security/correctness, code-quality, and does-it-reproduce), spawned in one message, then deduped into one verdict. Runs for EVERY item, no TRIVIAL/SMALL shortcut — it is 3 of the 6 roles in simplicio-tasks' minimum-agent floor. Use before…