Apache Magpie is a framework of agent-assisted workflows for maintaining Apache software projects, including issue triage, pull-request review, contributor mentoring, and security-report handling. Apache maintainers and developers use it to delegate repetitive project work to coding agents while retaining human review. Its catalogue entries are the skills, instructions, plugin, and settings that implement these workflows.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/apache/magpienpx agentmods add skills/apache/magpie/security-issue-deduplicateWrote 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/apache/magpie/security-issue-deduplicate)<a href="https://agentmods.dev/skills/apache/magpie/security-issue-deduplicate"><img src="https://agentmods.dev/badge/skills/apache/magpie/security-issue-deduplicate.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.07513 |
| Opus 5 | $0.00043 | $0.03757 |
| Sonnet 5 | $0.00017 | $0.01503 |
| Haiku 4.5 | $0.00009 | $0.00751 |
Grade A, and why
magpie-security-issue-deduplicate 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 3d 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 — 685 lines — stays where its author put it; the contents beside it link to each section on GitHub.
security-issue-deduplicate
Merges two <tracker> tracking issues that describe the
same underlying vulnerability. The output is a single tracker
("the kept issue") that carries every reporter's credit, every
mailing-list thread, and every independent report's body, with the
other tracker ("the dropped issue") closed and labelled
duplicate.
This is one of the few places in the security workflow where a
piece of reporter-supplied content (the dropped issue's body) moves
from one tracker to another. Since the target tracker is private to
<tracker>, no confidentiality boundary is crossed, but
the skill must still preserve every reporter's credit verbatim and
surface the merge in a status comment on both trackers so the audit
trail stays complete.
Golden rule — propose before applying. Every merge is a proposal: the skill computes the merged body, the two status comments, the label/close-issue actions, and the CVE-JSON regen command, and shows all of them to the user. Nothing is applied until the user confirms. There is no fast-path.
Golden rule — never merge across scopes. Two trackers with
different scope labels must not be merged. The set of scope
labels the project recognises comes from scope_detection.labels
in <project-config>/project.md
(cross-referenced from <project-config>/scope-labels.md).
For example, with scope labels <scope-a>, <scope-b>, and
<scope-c>, <scope-a> vs. <scope-b> or <scope-a> vs.
<scope-c> are the typical mismatches; other adopters declare
their own. If an external reporter rediscovers the same
bug in two different products' surfaces, that is a multi-scope
report and the resolution is a scope split handled by the
security-issue-sync skill, not a dedupe. This skill refuses to
operate when the two candidate trackers have different scope
labels, and the proposal says so explicitly.
Golden rule — every <tracker> / <upstream> reference is
clickable in the surface it lands on. Whenever this skill emits
a reference to either candidate tracker, a sibling tracker, or
any cited PR — the proposal shown before merge, the updated kept
issue body (which carries the duplicate's reporter-credit and
mailing-list-thread back-references), the closing comment on the
duplicate, the recap output — the reference must be one click
away in whatever surface it lands on:
-
On markdown surfaces (the updated kept issue body, the closing comment on the duplicate, the regenerated CVE JSON attachment's reference URLs): use the markdown link form per
AGENTS.md§ Linking tracker issues and PRs:- Kept / duplicate
<tracker>issues:[<tracker>#NNN](https://github.com/<tracker>/issues/NNN) <upstream>PR (e.g. cited fix):[<upstream>#NNN](https://github.com/<upstream>/pull/NNN)- Comment: link to the
#issuecomment-<C>anchor.
- Kept / duplicate
-
On terminal surfaces (the pre-merge proposal, the recap): wrap the visible short form in OSC 8 hyperlink escape sequences (
\e]8;;<URL>\e\\<short>\e]8;;\e\\) so modern terminals render the number itself as clickable. Where OSC 8 is unsupported (CI logs, dumb terminals), fall back to printing the bare URL on the same line after the number.
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.
- 3d ago First seen · 685 lines · 85 tokens per session scan A 8384e2f12051
magpie-security-issue-deduplicate is a skill published in the GitHub repository apache/magpie (87 stars, last pushed 5d ago), licensed Apache-2.0. It adds 85 tokens to every session and 7,513 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 2026-09-03.
Other skills, from other repositories
dast-nuclei
Fast, template-based vulnerability scanning using ProjectDiscovery's Nuclei with extensive community templates covering CVEs, OWASP Top 10, misconfigurations, and security issues across web applications, APIs, and infrastructure. Use when: (1) Performing rapid vulnerability scanning with automated CVE detection, (2)…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
CSOC Operations & Playbook Automation
SOC alert triage, incident playbook automation, escalation workflows, shift reporting, and SOC KPI tracking.