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 agentmods add skills/acn-ericlaw/agent-memory/apply-critiquenpx skills add acn-ericlaw/agent-memory --skill apply-critiquegit clone --depth 1 https://github.com/acn-ericlaw/agent-memoryWrote 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/acn-ericlaw/agent-memory/apply-critique)<a href="https://agentmods.dev/skills/acn-ericlaw/agent-memory/apply-critique"><img src="https://agentmods.dev/badge/skills/acn-ericlaw/agent-memory/apply-critique.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00899 |
| Opus 5 | $0.00033 | $0.00449 |
| Sonnet 5 | $0.00013 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
apply-critique 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 6d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apply-critique
⚠️ Tool-managed skill provided by agent-memory (
provenance: agent-memory-builtin). Don't edit it in place — it is overwritten on upgrade. To change behavior: fork it under a new skill name, or upstream a genuine fix to the agent-memory project (file an issue in its repo, or bring it to the tool maintainer) for back-port + validation. SeeSKILLS.md→ "Tool-provided (system) skills".
Consumes the critique a clean-memory reviewer hands back from a second-opinion review
and turns it into a bounded, validated set of changes — never an open autonomous loop.
The critique is advisory: it is one input, gated by deterministic checks and a human
decision.
When to use
After a fresh-context reviewer (a clean session or a different vendor) returns a critique of
a snapshot you generated with second-opinion. The human points you at the critique (a
pasted block or a review-scratch/critique-<UTC>.md file).
What to do
- Parse the critique into: critical issues, gaps, design feedback, execution guidance, risks, confidence. (The expected shape is below; tolerate a free-form critique by mapping it onto these buckets.)
- Plan a small, focused set of actions — only a handful of scoped changes that address the critical issues and execution guidance. A bounded repair, not a rewrite. State the plan before editing.
- Apply the scoped changes.
- Validate deterministically:
- the target's build / tests for code changes;
memory-lint(python3 agent-skills/memory-lint/scripts/memory-lint.py) if anymemory/file changed.- If neither gate applies (e.g. a docs-only change in a repo with no test suite and no
memory/edit), say so explicitly in the summary — the change then rests on judgment alone, which the human must know. This is exactly the failure mode the deterministic gate exists to prevent, so don't let "no gate fired" pass silently. A failing check blocks the change — fix or revert; do not paper over it.
- Summarize applied vs. rejected recommendations and why. A recommendation you
disagree with is fine to reject — say so explicitly. A genuine conflict you can't resolve
becomes a
- [ ] Contradiction:Open Thread (never-pick-a-winner), not a silent overwrite. The human gates the result. - Record it. A critique→repair cycle is a memory-relevant event → write a normal
session log with a
## Memory Referencessection (it stays inside the existing ritual, not beside it).
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.
- 6d ago First seen · 77 lines · 66 tokens per session scan A ab059c627ff7
apply-critique is a skill published in the GitHub repository acn-ericlaw/agent-memory (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 899 once invoked, about $0.0003 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
reelier-slice
Use when implementing any change to the Reelier authority ledger or Path C compiled-authority code - encodes the evidence-led slice loop, the baseline gate, the RED/GREEN review protocol, and the failure modes that have actually cost slices here.
reelier-replay
Freeze a repeatable, tool-call-driven task into a replayable Reelier skill, and replay an existing skill instead of redoing deterministic work. Use after finishing a task that was mostly API/MCP tool calls (data pulls, report generation, deploy checks, CRUD sequences) — never for arbitrary coding/file-edit sessions…
reelier-write-safety
Bound and record an agent's writes before granting them. Use when the user is adding or configuring an MCP server, planning to run an agent unattended or on a schedule or in CI, or deciding whether to give an agent write access to a real system. Covers the recorder, the policy seatbelt, approvals, and what a receipt…
reelier
Replay recurring deterministic jobs at 0 tokens instead of re-reasoning them every run. For cron/heartbeat tool-call workflows (status checks, data pulls, report generation, CRUD sequences) — record the job once with reelier, then run "npx -y reelier run " on every heartbeat and gate drift with "reelier diff". Never…
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.