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 synaptiai/synapti-marketplace --skill comprehension-reportgit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/comprehension-report)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/comprehension-report"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/comprehension-report/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/synaptiai/synapti-marketplace/comprehension-report"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/comprehension-report.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.01878 |
| Opus 5 | $0.00027 | $0.00939 |
| Sonnet 5 | $0.00011 | $0.00376 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade B, and why
comprehension-report scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=$(jq -r '.journal.dir // empty' "$HOME/.claude/settings.gh-workflow.json" 2>/dev/null) How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehension Report
Generates a structured narrative that helps humans understand what AI built, why it made the choices it did, and whether those choices align with the original intent.
Purpose
In a fully AI-driven workflow, code is produced faster than humans can read it. This skill bridges the gap by:
- Translating diffs into plain-language summaries
- Mapping acceptance criteria to implementation evidence
- Surfacing architecture decisions from the decision journal
- Identifying what humans should verify manually
Report Tiers
The report scales based on diff complexity. Complexity is determined from git diff --stat output.
| Diff Complexity | Report Level | Sections |
|---|---|---|
| < threshold lines, single area, docs/config only | Minimal — Summary + Requirements Adherence | 2 sections |
| threshold+ lines or multi-area or new modules | Full — All sections | 5 sections |
The threshold is configurable via .report.thresholdFull in settings. Default: 100 lines changed.
Process
Step 1: Gather Context
# Get current branch and issue number
BRANCH=$(git branch --show-current)
ISSUE_NUM=$(echo "$BRANCH" | grep -oE 'issue-[0-9]+' | grep -oE '[0-9]+')
# Get the default branch (consistent with gh-workflow commands)
DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name' 2>/dev/null)
[ -z "$DEFAULT_BRANCH" ] && DEFAULT_BRANCH="main"
# Get diff statistics to determine report tier
git diff --stat "$DEFAULT_BRANCH"...HEAD
git diff --numstat "$DEFAULT_BRANCH"...HEAD | awk '{ added += $1; removed += $2 } END { print "Lines added:", added, "Lines removed:", removed, "Total:", added + removed }'
# Get changed files with directory breakdown
git diff --name-only "$DEFAULT_BRANCH"...HEAD
# Get issue context
gh issue view "$ISSUE_NUM" --json title,body,labels 2>/dev/null
# Read journal directory from settings (local > project > user > default)
JOURNAL_DIR=$(jq -r '.journal.dir // empty' .claude/settings.gh-workflow.local.json 2>/dev/null)
[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=$(jq -r '.journal.dir // empty' .claude/settings.gh-workflow.json 2>/dev/null)
[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=$(jq -r '.journal.dir // empty' "$HOME/.claude/settings.gh-workflow.json" 2>/dev/null)
[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=".decisions"
# Read decision journal if it exists
cat "$JOURNAL_DIR/issue-$ISSUE_NUM.md" 2>/dev/null
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.
- yesterday First seen · 202 lines · 54 tokens per session scan B 7234f7a66471
comprehension-report is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,878 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other skills, from other repositories
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
independent-review-loop
Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustiveness — a reviewer…
x-spec
A system-planning guide that turns a vague idea into a set of linked design documents. It defines goals, modules, interfaces, data, workflows, and ways to check the result.
x-audit-arch
A project-wide architecture review skill that checks whether code is placed in the right modules and whether important definitions have one reliable source.
x-multi-llm-align
A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.