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 vitaliikapliuk/modelharness --skill memory-disciplinegit clone --depth 1 https://github.com/vitaliikapliuk/modelharnessWrote 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/vitaliikapliuk/modelharness/memory-discipline)<a href="https://agentmods.dev/skills/vitaliikapliuk/modelharness/memory-discipline"><img src="https://agentmods.dev/badge/skills/vitaliikapliuk/modelharness/memory-discipline/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/vitaliikapliuk/modelharness/memory-discipline"><img src="https://agentmods.dev/badge/skills/vitaliikapliuk/modelharness/memory-discipline.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 | $0.00042 | $0.00323 |
| Opus 5 | $0.00021 | $0.00161 |
| Sonnet 5 | $0.00008 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
memory-discipline 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 10d 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.
What it actually says
Memory Discipline
Fable 5 performs notably better when it can write learnings somewhere for future reference. Give Opus the same surface and rules.
Read rules
- At the start of non-trivial work, read
MEMORY.md(index) if present, then anylessons/*.mdwhose one-line summary looks relevant. - Memories reflect what was true when written — verify a referenced file/flag still exists before relying on it.
Write rules
- One lesson per file in
lessons/, kebab-case name, one-line summary on the first line. - Record corrections from the user and confirmed working approaches alike — include WHY it mattered, not just what happened.
- Don't save what the repo already records (code structure, git history, README facts).
- Update an existing lesson rather than creating a near-duplicate; delete lessons that turn out to be wrong.
- After writing, add/refresh a one-line pointer in
MEMORY.md.
Format
<!-- lessons/use-fake-clock-in-timer-tests.md -->
Timer tests must inject a fake clock — real sleeps made CI flaky.
Context: PR #42 reverted twice. `time.monotonic` is patched via the `clock`
parameter; never call `time.sleep` in tests.
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.
- 10d ago First seen · 33 lines · 42 tokens per session scan A 6827318174c2
memory-discipline is a skill published in the GitHub repository vitaliikapliuk/modelharness (38 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 323 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
agent-common
Shared preamble loaded by all cc10x agents — memory protocol, contract format, output rules.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.