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 leifericf/agentic-sdk --skill check-memorygit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/leifericf/agentic-sdk/check-memory)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/check-memory"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-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/leifericf/agentic-sdk/check-memory"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-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 | $0.00036 | $0.01081 |
| Opus 5.5 | $0.00014 | $0.00432 |
| Sonnet 5.5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
check-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 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
check-memory
Role: review the assigned C or Zig module for memory defects.
Failure model: an allocation outlives its owner, a borrow outlives its backing memory, or a GC-visible pointer is held across an allocation point without a guard; the bug that ships is the path that skips a free or the scanner happens to hide.
Active only when the descriptor's :languages includes :c or :zig.
Read the ownership rules in
skills/shared/references/architecture.md (the C and Zig sections) and
any project-specific known-pitfalls note before sweeping.
The bug class splits by language.
Look for
C (GC or manual ownership)
- GC windows. Any GC-visible pointer or raw buffer held across an allocation point without a pin or a depth guard. Check pin and unpin pairing on every path, including the error path (the save-stack assertion often fires only in debug builds).
- Ownership violations.
freeon a GC-owned value; a GC value stored in host-owned memory the tracer cannot see; a peek or get result freed or retained past the next collection; a take result leaked. - realloc misuse.
p = realloc(p, n)without a temp; the old block leaks when realloc fails. - Error-path leaks. For each early return or longjmp out of a function that allocated host memory: what frees it?
- Write-barrier gaps. Direct stores into old-generation objects that bypass the barrier (mutation outside the provided mutators).
Zig (explicit allocators, no GC)
- Missing defer or errdefer. Every heap allocation must have a
matching free reachable on every path.
deferfor the success path;errdeferfor the partial-construction path before ownership transfers to the caller. Check each early return, eachtry, each error exit: what frees the buffers allocated above it? - Wrong allocator for the phase. A per-node scratch allocated from the execution allocator (or vice versa); a value meant to outlive parsing allocated from the parse arena; a long-lived entry on a short-lived arena. Match the allocation to its phase.
- Slices and pointers outliving backing memory. A slice returned
from or stored past the
deinitof the allocator that produced it; a sub-slice retained after the parent is freed; a value that aliases a freed source buffer. - init and deinit pairing. Every type with an init or alloc constructor needs a deinit that frees exactly what it owns, called on every path. Double-free (freeing a borrowed slice the owner also frees); missing-free (a field allocated in init not released in deinit).
- Allocator passed explicitly. No hidden global allocator; the allocator is a parameter threaded through. Flag any subsystem that reaches for a package-level allocator instead of the one its caller passed.
- Alignment and realloc. An
@alignCastwithout a real guarantee; a realloc whose result is dropped on failure (the old block leaks).
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 First seen · 110 lines · 36 tokens per session scan A 3eecbd2b9a10
check-memory is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,081 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…