agentmods.dev

agents-remember: Skill for Claude Code

.agents/skills/c-02-memory-quality-control/SKILL.md

c-02-memory-quality-control is a skill for Claude Code, Codex from Foxfire1st/agents-remember. It costs 29 tokens per session (2,367 once invoked), scanned A, original, MIT.

A repository check for deciding whether an agent's stored project notes are trustworthy and up to date. It checks for drift, missing onboarding files, and problems before changes are committed.

In plain words
What is it for?
It is for checking memory at task start, listing missing onboarding work, reviewing new files before a code commit, and producing a final memory-quality report.
Why use it?
It helps prevent agents from relying on outdated notes or committing source files without the related onboarding information. It also identifies cleanup needed before closing work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Foxfire1st/agents-remember's own configuration. It tells Claude Code and Codex how to work on agents-remember itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-remember configures →

not rated 39repo changed 1mo ago A scan SkillSpector: pass 29 tokens original MIT
View source ↗ Foxfire1st/agents-remember foxfire1st.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to Foxfire1st/agents-remember. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Foxfire1st/agents-remember/main/.agents/skills/c-02-memory-quality-control/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Foxfire1st/agents-remember

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for c-02-memory-quality-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-02-memory-quality-control/github.svg)](https://agentmods.dev/skills/foxfire1st/agents-remember/c-02-memory-quality-control)
Your own site
<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/c-02-memory-quality-control"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-02-memory-quality-control/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.

agentmods 80×15 button for c-02-memory-quality-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/c-02-memory-quality-control"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-02-memory-quality-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.02367
Opus 5.5 $0.00012 $0.00947
Sonnet 5.5 $0.00006 $0.00473
Haiku 4.5 $0.00003 $0.00237

Measured 1mo ago against content hash 64906cb16441, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

c-02-memory-quality-control 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.

.agents/skills/c-02-memory-quality-control/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

c-02-memory-quality-control Memory Quality Control

Use this skill when the developer explicitly requests memory-quality evidence or when an approved workflow asks for a scoped diagnostic. Closeout and integration consume prepared code/memory/ledger Git inputs and do not invoke this skill as a quality prerequisite.

The skill owns the diagnostic procedure. Drift detection can qualify task-start context, and curators can run scoped onboarding checks before handoff. Full memory quality remains an explicit developer-requested operation.

Inputs

This skill operates on one repository at a time and starts from the context resolved by c-08-ar-coordination-context-resolver or MCP resolve_context.

Primary Outputs

  1. task-start trust guidance from repo-wide drift classification
  2. a concrete onboarding maintenance worklist for c-05-create-or-update-onboarding-files
  3. a scoped missing-onboarding report when a curator requests it
  4. an on-demand memory-quality report covering the requested scope
  5. explicit next actions when the requested diagnostic is not clean

Quality Control Phases

Phase Check Purpose
Task start (when requested) drift_check Qualify existing onboarding before planning against it.
Curator handoff scoped c-05-create-or-update-onboarding-files checks Maintain affected sidecars, overviews, indexes, and entity entries for this change.
Explicit developer request memory_quality_check Run the requested memory-quality scope and report every passed, failed, blocked, and not-run check.
Targeted style repair history_order_fix.py Fix an identified ordering issue only after the requested report names it.

Diagnostics are evidence only. They should not become an automatic closeout or integration gate.

Boundaries

  1. This skill reports and routes memory quality work; it does not rewrite onboarding prose itself.
  2. It does not replace deep Research.
  3. It does not decide requirement or architecture direction.
  4. It should qualify stale onboarding rather than silently treating it as trustworthy.
  5. It must not turn the default repo-wide drift diagnostic into a whole-repository adoption scan for files that never had onboarding.
  6. It must not treat implementation approval as commit approval; closeout commits remain owned by the c-09-git-worktree-manager skill transaction and authority controls.
  7. It must not make a memory-quality, curator, or review result a closeout or integration prerequisite.

Read the full file on GitHub · 251 lines

Changes

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.

  1. 1mo ago Changed · -17 lines · -5 tokens per session 64906cb16441
  2. 2mo ago First seen · 268 lines · 34 tokens per session scan A e5595d71a6c0

Subscribe to this mod's changes

c-02-memory-quality-control is a skill published in the GitHub repository Foxfire1st/agents-remember (39 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 2,367 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.

Building agentsMemory and contextOrchestrationagent-memory-systemagentic-control-planebitemporalcodegraphsemantic-search
Related

c-02-memory-quality-control compared with skills from other repositories

c-02-memory-quality-control next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
c-02-memory-quality-controlFoxfire1st/agents-rememberSkill39yesterdayMITA29Claude Code, Codex
remember-sessiondoobidoo/mcp-memory-serviceSkill2.1kyesterdayApache-2.0A68Claude Code
memwalMystenLabs/MemWalSkill12118d agoApache-2.0A80Claude Code, Codex
cortex-profilecdeust/CortexSkill76todayMITA98Claude Code
cortex-remember-globalcdeust/CortexSkill76todayMITA99Claude Code
cortex-consolidatecdeust/CortexSkill76todayMITA84Claude Code
cortex-explore-memorycdeust/CortexSkill76todayMITA91Claude Code