sharpen

A conversation review command that looks for inefficient agent behavior and records concrete improvements as project knowledge.

In plain words
What is it for?
Use it to analyze a conversation, propose fixes, confirm them with the user, and write approved guidance and an audit record.
Why use it?
It helps identify repeated workflow problems and turn them into agreed changes instead of leaving them as one-off observations.

Command

Install

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.

agentmods
npx agentmods add commands/vladolaru/claude-code-plugins/sharpen
Clone the repo
git clone --depth 1 https://github.com/vladolaru/claude-code-plugins
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.01996
Opus 5 $0.00008 $0.00998
Sonnet 5 $0.00003 $0.00399
Haiku 4.5 $0.00002 $0.00200

Measured 2d ago against content hash 9ba1adc805e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sharpen 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 2d 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.

plugins/dex/commands/sharpen.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dex:sharpen

Analyze agent behavior in the current conversation, find inefficiencies, and capture concrete fixes as project knowledge. This is an operational extraction strategy — it captures how the agent should work, not domain knowledge about the codebase.

digraph sharpen_flow {
    "Start" [shape=doublecircle];
    ".claude/docs/ exists?" [shape=diamond];
    "User wants scaffolding?" [shape=diamond];
    "Create directories" [shape=box];
    "Stop" [shape=doublecircle];
    "Sub-agents dispatched?" [shape=diamond];
    "Run analyzer" [shape=box];
    "Scan conversation for inefficiencies" [shape=box];
    "Inefficiencies found?" [shape=diamond];
    "Nothing found — stop" [shape=doublecircle];
    "Classify and draft fixes" [shape=box];
    "Confirm with user" [shape=box];
    "Write docs + update audit log" [shape=box];
    "Any fix rule-worthy?" [shape=diamond];
    "Offer promotion" [shape=box];
    "Done" [shape=doublecircle];

    "Start" -> ".claude/docs/ exists?";
    ".claude/docs/ exists?" -> "Sub-agents dispatched?" [label="yes"];
    ".claude/docs/ exists?" -> "User wants scaffolding?" [label="no"];
    "User wants scaffolding?" -> "Create directories" [label="yes"];
    "User wants scaffolding?" -> "Stop" [label="no"];
    "Create directories" -> "Sub-agents dispatched?";
    "Sub-agents dispatched?" -> "Run analyzer" [label="yes"];
    "Sub-agents dispatched?" -> "Scan conversation for inefficiencies" [label="no"];
    "Run analyzer" -> "Scan conversation for inefficiencies";
    "Scan conversation for inefficiencies" -> "Inefficiencies found?";
    "Inefficiencies found?" -> "Nothing found — stop" [label="no"];
    "Inefficiencies found?" -> "Classify and draft fixes" [label="yes"];
    "Classify and draft fixes" -> "Confirm with user";
    "Confirm with user" -> "Write docs + update audit log" [label="accepted"];
    "Confirm with user" -> "Stop" [label="skip"];
    "Write docs + update audit log" -> "Any fix rule-worthy?";
    "Any fix rule-worthy?" -> "Offer promotion" [label="yes"];
    "Any fix rule-worthy?" -> "Done" [label="no"];
    "Offer promotion" -> "Done";
}

Read the full file on GitHub · 190 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. 2d ago First seen · 190 lines · 15 tokens per session scan A 9ba1adc805e3

Subscribe to this mod's changes

sharpen is a command published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 1,996 once invoked, about $0.0001 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.