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 leifericf/agentic-sdk --skill apply-findingsgit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/leifericf/agentic-sdk/apply-findings)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/apply-findings"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/apply-findings.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 | $0.00032 | $0.00724 |
| Opus 5 | $0.00016 | $0.00362 |
| Sonnet 5 | $0.00006 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
apply-findings 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apply-findings
Fix the punch-list items assigned to you (one module, one fix level), one commit per finding or tightly-related group. You are the sole mutator in a fix loop.
Procedure
Per finding:
- Confirm it first. Read the cited code; reproduce if a repro is
suggested (a failing test, an eval form, a malformed fixture, a lane
run with the offending input). A finding you cannot confirm goes
back as
FAILED <id>: not reproducible, <why>rather than a speculative edit. - Smallest sufficient edit. Fix exactly the defect. At the
:correctnesslevel do not also rename or refactor; that is the factoring wave's job and it makes the diff unreviewable. At:factoringor:stylethe finding defines the scope. - Stay in bounds. Your module directory plus its own test
namespace. If the real fix lives in another module or the public
surface (a public API, the native boundary contract in
references/architecture.md), returnneeds-cross-module <id>; do not write the tempting local workaround. That is exactly the fix the no-workarounds rule bans. - Test the fix. A correctness fix gets a regression test in the
right surface (
write-tests) unless one already covers it; "the reviewer found it" means the suite did not. For a persistence fix, the regression exercises the store's transaction and history behavior. For a native fix, the round-trip integration test that compiles and calls real native code. - Verify. The owning tests always; the full suite if the fix could touch a caller; the changed language's format and lint lanes; if the fix touched the native edge, the round-trip integration test.
- Land. Commit
Category: Imperative summarywith jj (jj describe, thenjj new) and fold it into the stack by change id (jj squashorjj rebase). Never editCHANGELOG.mdor version fields. RETURN your changelog lines; the round runner collects them. Changelog lines followwrite-changelog(user-visible effects only; no line is normal for a style or factoring fix). If the project is alpha or beta, write-changelog refuses and returns no line; return none yourself.
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 · 64 lines · 32 tokens per session scan A 222c8c50af82
apply-findings is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 724 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 2026-08-31.
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.