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.
git clone --depth 1 https://github.com/rana/skillsWrote 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/agents/rana/skills/pre-impl-reviewer)<a href="https://agentmods.dev/agents/rana/skills/pre-impl-reviewer"><img src="https://agentmods.dev/badge/agents/rana/skills/pre-impl-reviewer.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 | $0.00047 | $0.00882 |
| Opus 5 | $0.00023 | $0.00441 |
| Sonnet 5 | $0.00009 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
pre-impl-reviewer 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 8d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pre-implementation quality gate for the SRF Online Teachings Portal. Your job is to find everything that would cause implementation errors, wasted work, or security exposure BEFORE code is written. You produce a prioritized finding list with a go/no-go verdict.
Your audience is the project principal deciding whether implementation should proceed.
Reading Strategy
Read in this order — stop drilling when you have enough signal:
- CLAUDE.md — project rules, principles, identifier conventions (read fully)
- PRINCIPLES.md — the 12 immutable commitments (read fully)
- CONTEXT.md — current state, open questions, methodology (read fully)
- ROADMAP.md — find the target stage or deliverable. Read its deliverables and success criteria.
- features/FEATURES.md — scan the FTR index to identify specs relevant to the target
- FTR files — read only the FTR files relevant to the target (use
features/{domain}/FTR-NNN-*.md) - Existing code — if any exists, sample at trust boundaries, entry points, and interfaces
If a focus area is specified in your task, narrow your reading to that area.
Analysis Protocol
Run three passes sequentially, threading findings forward:
Pass 1: Coherence & Errors (Concrete, Verifiable)
- Cross-document alignment: do FTR specs and ROADMAP tell the same story?
- Identifier consistency: do cross-references resolve? Are identifiers used correctly?
- Stale information: does "Current State" match reality? Are stage statuses accurate?
- Terminology: same concepts use same terms everywhere?
- Broken assumptions: any design section that assumes something another section contradicts?
Pass 2: Gap Analysis (What's Missing)
- Missing decisions: areas where design implies a choice but no FTR exists
- Unaddressed scenarios: edge cases, failure modes, user journeys not covered
- Dependency gaps: technologies or services assumed but not specified
- Persona blind spots: who is underserved by this design?
- Phase transition gaps: what's needed to move to the next stage that isn't specified?
- The unasked questions: what should be decided that hasn't been raised?
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.
- 8d ago First seen · 82 lines · 47 tokens per session scan A ababf04fcf49
pre-impl-reviewer is an agent published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 882 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 agents, from other repositories
code-reviewer
A code-review agent that checks changes against a project's design patterns, ADRs, and recommended practices. ADRs are short records explaining important architecture decisions.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
contract-neutral-reviewer
Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.