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 zszz3/AgentRecall --skill dsh-find-simplificationsgit clone --depth 1 https://github.com/zszz3/AgentRecallWrote 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/zszz3/agentrecall/dsh-find-simplifications)<a href="https://agentmods.dev/skills/zszz3/agentrecall/dsh-find-simplifications"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/dsh-find-simplifications/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/zszz3/agentrecall/dsh-find-simplifications"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/dsh-find-simplifications.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00627 |
| Opus 5 | $0.00021 | $0.00313 |
| Sonnet 5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
dsh-find-simplifications 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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Simplifications
Turn a broad cleanup request into a small set of well-supported changes or proposals that reduce owned code, APIs, states, and maintenance obligations while preserving current product behavior.
Establish context
Read the applicable repository instructions, architecture documentation, tests, and durable design records before judging a subsystem. Identify intentional seams, supported variants, compatibility promises, generated surfaces, and user-visible behavior that must remain.
Tests and design records are evidence, not unquestionable truth. A test that only protects unused behavior may be removed with that behavior; a recorded compatibility or data-format obligation requires stronger evidence before changing it.
Strong candidates
- A public method, event, option, helper, package, or durable field has no production consumer.
- Tests or documentation are the only consumers and do not protect a current obligation.
- Multiple representations or state flags mirror the same authoritative fact.
- An abstraction exists for one caller without isolating a meaningful lifecycle, safety, transaction, or ownership decision.
- Compatibility, retry, rollback, or defensive machinery protects a scenario the product does not support.
- A maintained dependency or platform builtin would remove substantial implementation and dedicated tests with little glue remaining.
- A feature implements speculative generality without a current product owner or execution path.
Complex code, a large file, one unused-looking symbol, or a tool report alone is not sufficient evidence.
Prove or reject a candidate
- Search exact symbols, strings, configuration keys, dynamic registrations, loaders, subprocess entries, and package exports.
- Classify consumers as production, test/documentation, generated, or ambiguous; inspect ambiguous examples and scripts before deciding.
- Trace both sides of changed interfaces and identify the user-visible behavior, durable data, lifecycle owner, and failure semantics.
- For asynchronous code, map timers, listeners, processes, leases, abort signals, readiness promises, and cleanup paths to distinct owners and transitions.
- For validators and defensive copies, identify where data becomes untrusted or crosses a real process, persistence, network, model, or user-input boundary.
- Reject the candidate when a current production caller exists and removal would be a feature decision rather than cleanup.
- Compare net deletion against replacement glue, migrations, documentation churn, and new failure modes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 51 lines · 42 tokens per session scan A 8146bcaaf503
dsh-find-simplifications is a skill published in the GitHub repository zszz3/AgentRecall (764 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 627 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…