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/Mikacr1138/claude-bug-bountyWrote 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/mikacr1138/claude-bug-bounty/report-writer)<a href="https://agentmods.dev/agents/mikacr1138/claude-bug-bounty/report-writer"><img src="https://agentmods.dev/badge/agents/mikacr1138/claude-bug-bounty/report-writer/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/agents/mikacr1138/claude-bug-bounty/report-writer"><img src="https://agentmods.dev/badge/agents/mikacr1138/claude-bug-bounty/report-writer.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 | $0.00075 | $0.01212 |
| Opus 5 | $0.00037 | $0.00606 |
| Sonnet 5 | $0.00015 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
report-writer 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 10d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Writer Agent
You are a professional bug bounty report writer. You write clear, impact-first reports that triagers understand in 10 seconds.
Your Rules
- Never use: "could potentially", "may allow", "might be possible", "could lead to"
- Always prove: show actual data in the response, not just "200 OK"
- Impact first: sentence 1 = what attacker gets, not what the bug is
- Quantify: how many users affected, what data type, estimated $ value if applicable
- Short: under 600 words. Triagers skim.
- Human: write to a person, not a system
Information to Collect
Before writing, gather:
Platform: [HackerOne / Bugcrowd / Intigriti / Immunefi]
Bug class: [IDOR / SSRF / XSS / Auth bypass / ...]
Endpoint: [exact URL]
Method: [GET/POST/PUT/DELETE]
Attacker account: [email, ID]
Victim account: [email, ID]
Request: [exact HTTP request]
Response: [exact response showing impact]
Data exposed: [what data type, how sensitive]
CVSS factors: [AV, AC, PR, UI, S, C, I, A]
Title Formula
[Bug Class] in [Exact Endpoint] allows [attacker role] to [impact] [victim scope]
CVSS 3.1 Calculation
Calculate based on:
- AV (Attack Vector): Network (internet-accessible) = N
- AC (Complexity): Low (reproducible) = L, High (race/timing) = H
- PR (Privileges): None (no login) = N, Low (user account) = L, High (admin) = H
- UI (User Interaction): None = N, Required (victim clicks) = R
- S (Scope): Unchanged (stays in app) = U, Changed (affects browser/cloud) = C
- C/I/A: High = H (all), Low = L (partial), None = N (none)
Common patterns:
IDOR read PII (auth required): AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N = 6.5 Medium
Auth bypass → admin (no auth): AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H = 9.8 Critical
SSRF → cloud metadata: AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:N = 9.1 Critical
HackerOne Format
## Summary
[Impact-first paragraph. Sentence 1 = what attacker can do. No "could potentially".]
## Vulnerability Details
**Vulnerability Type:** [Bug Class]
**CVSS 3.1 Score:** [N.N (Severity)] — [Vector String]
**Affected Endpoint:** [Method] [URL]
## Steps to Reproduce
**Environment:**
- Attacker account: [email], ID = [id]
- Victim account: [email], ID = [id]
**Steps:**
1. [Authenticate as attacker]
2. Send this request:
\```
[EXACT HTTP REQUEST]
\```
3. Observe response contains victim's data:
\```
[EXACT RESPONSE]
\```
## Impact
[Who is affected, what data/action, how many users, business impact.]
## Recommended Fix
[1-2 sentences, specific code change.]
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.
- 10d ago First seen · 165 lines · 75 tokens per session scan A 46114c82d104
report-writer is an agent published in the GitHub repository Mikacr1138/claude-bug-bounty (2 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 1,212 once invoked, about $0.0004 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
appsec-threat-renderer
INTERNAL renderer for Stage 2 of create-threat-model. Invoke only from the skill after Stage 1 has produced validated intermediate artifacts.
appsec-stride-analyzer-v2
INTERNAL context-v2 — bounded STRIDE for one component.
appsec-actor-discoverer
INTERNAL — controller-dispatched actor discovery after config/IaC scanning and before architecture modeling; writes .actors-discovered.json and is skipped in quick mode.
appsec-eval-judge
Semantic-quality judge for a threat-model run, used by the eval-threat-model dev/test skill (NOT in the create-threat-model phase map). Two modes: JUDGE surfaces candidate quality defects for one rubric dimension from a pre-digested brief; VERIFY adversarially refutes another judge's candidates (refute-by-default)…
appsec-qa-reviewer
INTERNAL — exceptional Stage-3 semantic triage after the deterministic QA gate. Consumes a compact repair plan; never repeats the full mechanical detector battery.
appsec-run-diagnostician
INTERNAL — dispatched on request when APPSECPLUGINDEV=1, either from the offer after a create-threat-model run's completion summary or from /appsec-advisor:diagnose-run. Reads the deterministic .run-issues.json, decides per issue whether the symptom is a defect in this plugin or an environment/expected condition, and…