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 kalpmodi/akira --skill reportgit clone --depth 1 https://github.com/kalpmodi/akiraWrote 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/kalpmodi/akira/report)<a href="https://agentmods.dev/skills/kalpmodi/akira/report"><img src="https://agentmods.dev/badge/skills/kalpmodi/akira/report.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 | $0.00054 | $0.01554 |
| Opus 5 | $0.00027 | $0.00777 |
| Sonnet 5 | $0.00011 | $0.00311 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Generator
Overview
Reads triage.md (required) and session.json to produce a structured report.
80-90% of content is pre-filled from report_draft.findings[] - this skill formats and narratizes, it does not discover.
Steps
-
Get target and report mode from user if not provided.
- Ask: "Full pentest report or Bug Bounty submission format (HackerOne/Bugcrowd)?"
-
Read triage.md (required):
cat ~/pentest-toolkit/results/<target>/triage.mdIf missing: stop and tell the user to run
/triage <target>first. -
Read session.json for Scalpel stats:
SESSION=~/pentest-toolkit/results/<target>/session.json SCALPEL_SCORE=$(jq -r '.scalpel.snr.scalpel_score // "N/A"' $SESSION 2>/dev/null) CERTIFIED=$(jq '.report_draft.findings | map(select(.status=="SCALPEL_CERTIFIED")) | length' $SESSION 2>/dev/null) -
Read plan.md (optional):
cat ~/pentest-toolkit/results/<target>/plan.md 2>/dev/null -
Get today's date:
date +%Y-%m-%d -
Write report to
~/pentest-toolkit/results/<target>/report-<YYYY-MM-DD>.md:
# Penetration Test Report: <target>
**Date:** <YYYY-MM-DD>
**Assessor:** Akira / Red Team
---
## Scalpel Assessment Quality
| Metric | Value |
|--------|-------|
| Scalpel Score | <N>/100 |
| Certified Findings (SCL) | <N> |
| False Positives | 0 |
| KCCG Complete | <N>/<N> |
> Every finding below is Scalpel Certified — 5-layer Precision Gate passed,
> full Kill Chain proven, DNA fingerprinted, PoC generated.
---
## Executive Summary
**Scope:** <from plan.md, or "Quick engagement — no scope document recorded">
**Assessment Period:** <date>
<2-3 sentence summary of most critical certified findings and overall risk posture>
**Findings Summary:**
| Severity | SCL Certified | Potential |
|----------|--------------|-----------|
| Critical | <N> | <N> |
| High | <N> | <N> |
| Medium | <N> | <N> |
| Low | <N> | <N> |
---
## Certified Findings
### [SCL-YYYY-NNN] <Title>
SCALPEL CERTIFIED [SCL-YYYY-NNN] Severity: <Critical|High|Medium|Low> KCCG: /5 ( certified) Confidence: / 100 DNA: ... PoC: pocs/_poc.sh
**Severity:** <severity>
**CVSS Estimate:** <score> (AV:N/AC:L/PR:N/UI:N/...)
**Asset:** <affected endpoint>
**Weakness:** CWE-<N> — <name>
**Description:** <what the vulnerability is>
**Kill Chain:**
1. <step 1: technique and action>
2. <step 2: technique and action>
3. <step 3: technique and action>
**Impact:** <business impact — specific: "An attacker can extract AWS IAM credentials and access production S3 buckets containing customer database backups">
**Evidence:**
<direct HTTP response quote or tool output — must be from kill_chain evidence>
**Steps to Reproduce:**
```bash
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 · 202 lines · 54 tokens per session scan A 5eb54ef449f2
report is a skill published in the GitHub repository kalpmodi/akira (21 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,554 once invoked, about $0.0003 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
pwnote-offsec-pen200
Use whenever the user is working on Offsec's PEN-200 course/OSCP — PWK lab notes, exam report drafting, screenshot/evidence discipline, or exam flag handling. Trigger on "OSCP", "PEN-200", "PWK", "OSCP exam report", or "proof.txt", even without the word "skill".
PDF files: create, read, merge, fill, OCR, edit text.
pdf-toolkit
Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…
extracting-lab-tables
Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
liteparse
Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally without cloud dependencies.