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 forefy/.context --skill pre-bountygit clone --depth 1 https://github.com/forefy/.contextWrote 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/forefy/.context/pre-bounty)<a href="https://agentmods.dev/skills/forefy/.context/pre-bounty"><img src="https://agentmods.dev/badge/skills/forefy/.context/pre-bounty/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/forefy/.context/pre-bounty"><img src="https://agentmods.dev/badge/skills/forefy/.context/pre-bounty.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.02108 |
| Opus 5 | $0.00018 | $0.01054 |
| Sonnet 5 | $0.00007 | $0.00422 |
| Haiku 4.5 | $0.00004 | $0.00211 |
Grade A, and why
pre-bounty 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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-bounty: scope recon & target prioritization
The core thesis
Most hunters converge on whatever is cheapest to start testing. That means the crowd is an artifact of the setup barrier, not of where the bugs are. So the edge is systematic: rank the scope by
opportunity ≈ (payout ceiling × freshness) ÷ crowd, with setup difficulty acting as a moat - a hard-to-reproduce environment keeps competitors out, so it is a positive when paired with a high ceiling.
The whole skill exists to compute that ranking from real program data and show it in a way the user can act on. A high max-payout asset that is trivial to set up and already swept (lots of resolved reports) is a worse target than a modest one nobody has tooled up for. Make that legible.
Inputs this skill accepts
Any of, in order of preference:
- A program URL -
hackerone.com/<program>,bugcrowd.com/<program>,app.intigriti.com/...,yeswehack.com/..., or a self-hosted/security/security.txt/ VDP page. - A pasted scope table or asset list (domains, mobile apps, repos, APIs).
- A rough description of API/repo access the user already has.
If you only get a program name, construct the URL. If the platform page is
JavaScript-rendered (HackerOne, Bugcrowd, Intigriti all are), use the browser
tools to read it - WebFetch returns an empty shell for these. read_page /
get_page_text on the policy and scope tabs is the reliable path.
Workflow
Work the five stages in order. Stages 1–3 are parallelizable - fire the fetches and searches together.
1. Gather the scope (the signal-richest step)
Pull and record, per asset:
- Asset name, type (domain / mobile / desktop / API / source / other) and whether it is in or out of scope.
- Payout tier - most programs tag assets into tiers (HackerOne Core/Non-core; Bugcrowd P1–P5 targets; others "critical eligible" vs not). Capture the max reward reachable per asset - this is the ceiling.
- Resolved-report count / share per asset if the platform shows it. This is your single best crowd proxy - an asset with 40% of all resolved reports is picked-over; one with <2% is open. HackerOne shows this on the scope table; Bugcrowd/Intigriti show submission stats less granularly (note when missing).
- Last-updated date of each scope entry → freshness. Recently added or rescoped assets have had fewer eyes.
- Program-wide reward table (per-severity bounty ranges + averages) and the severity mix of resolved reports if shown.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 154 lines · 37 tokens per session scan A 3f2cf06708c1
pre-bounty is a skill published in the GitHub repository forefy/.context (144 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 2,108 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 2026-08-30.
Other skills, from other repositories
eresus-manual-security-audit
Elite manual security code review skill for deep, adversarial vulnerability hunting and exploit-chain discovery. Trigger when the user asks to: "do a deep security audit", "manual code review", "find exploit chains", "hunt for logic bugs", "red-team this codebase", "do an offensive security review", "review this like…
eresus-sast-scanner
General-purpose Static Application Security Testing (SAST) skill for code vulnerability analysis. Trigger when the user asks to: "analyze code for vulnerabilities", "review code security", "find security bugs", "do a SAST scan", "check for [vulnerability type] in code", "audit source code", or requests a security code…
eresus-php-audit
Deep PHP-specific security audit skill covering injection, deserialization, file operations, auth bypass, POP chain discovery, and CMS-specific patterns. Trigger when auditing PHP code: "audit this PHP app", "find PHP security issues", "check Laravel/WordPress for vulnerabilities", "PHP SAST review", "check for PHP…
eresus-python-audit
Deep Python-specific security audit skill with 50+ vulnerability class coverage across 7 categories. Trigger when auditing Python code: "audit this Python app", "find Python security issues", "check Flask/Django for vulnerabilities", "Python SAST review", "check for pickle vulnerabilities", "review this FastAPI code".…
eresus-remediator
Security remediation skill for fixing confirmed or likely SAST findings in source code. Trigger when the user asks to: "fix a vulnerability", "patch this security bug", "remediate SAST findings", "harden this endpoint", "make this auth flow safe", or wants code changes that remove a confirmed security issue while…
eresus-variant-analysis
GHSA/CVE variant analysis workflow for finding similar vulnerability patterns across a codebase. Trigger when the user asks to: "find variants of this CVE", "GHSA variant analysis", "find similar bugs", "hunt for the same pattern", "are there other places with this vulnerability?", or when a known vulnerability is…