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 xD4O/praxis --skill codebase-comprehensiongit clone --depth 1 https://github.com/xD4O/praxisWrote 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/xd4o/praxis/codebase-comprehension)<a href="https://agentmods.dev/skills/xd4o/praxis/codebase-comprehension"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/codebase-comprehension/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/xd4o/praxis/codebase-comprehension"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/codebase-comprehension.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 | $0.00105 | $0.00929 |
| Opus 5.5 | $0.00042 | $0.00372 |
| Sonnet 5.5 | $0.00021 | $0.00186 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
codebase-comprehension 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 15d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Comprehension Protocol
EXTREMELY_IMPORTANT: This is a MANDATORY protocol, not a suggestion. Follow every step. Do not skip steps. Do not combine steps. Do not summarize. Work through each gate in order.
The expensive bugs are not in the line you change — they are in the caller three files away that depended on the behavior you just changed. This protocol forces you to map the blast radius before you touch anything.
STEP 1 — Locate entry points and the change site
Identify how execution reaches the code you intend to change: who calls it, from where, and under what conditions. If you cannot say how the code is reached, you cannot predict what your change affects.
STEP 2 — Trace the data flow through the change site
Follow the actual values through the code you will touch: what comes in, what is read or mutated, what goes out, and in what units/shape/type. State it explicitly — do not assume the values are what the names suggest.
STEP 3 — Enumerate every consumer of what you will change
List everything that depends on the current behavior or shape: callers, subscribers, tests, serialized formats, anything downstream. This set IS the blast radius. "It's just a small change" is a claim about this list — so produce the list.
STEP 4 — Name at least one thing that could break elsewhere
From the blast radius, state a concrete failure the change could cause OUTSIDE the code you are editing — a specific caller that passes values differently, a consumer relying on the old shape. "Nothing else is affected" is allowed only after STEP 3 produced an empty consumer set and you say so.
STEP 5 — Report
COMPREHENSION: [code to change]
├── Entry points: [how execution reaches it]
├── Data flow: [in → transform → out, with shapes/units]
├── Blast radius: [every consumer of current behavior/shape]
├── At-risk elsewhere: [≥1 concrete off-site failure the change could cause]
└── Confidence: [HIGH / MEDIUM / LOW]
Confidence: HIGH — full call graph and data flow traced, blast radius complete. MEDIUM — main paths traced, some dynamic/indirect callers unverified. LOW — the code is reached by paths you cannot fully see; widen the trace before editing.
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.
- 15d ago First seen · 86 lines · 105 tokens per session scan A fdee4f9b5f77
codebase-comprehension is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 929 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
gsd-ns-review
quality gates | code review debug audit security eval ui.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.