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 kennethkhoocy/applied-micro-skills --skill cite-placementgit clone --depth 1 https://github.com/kennethkhoocy/applied-micro-skillsWrote 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/kennethkhoocy/applied-micro-skills/cite-placement)<a href="https://agentmods.dev/skills/kennethkhoocy/applied-micro-skills/cite-placement"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/cite-placement/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/kennethkhoocy/applied-micro-skills/cite-placement"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/cite-placement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 61 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 63 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 75 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 81 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 142 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 170 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00181 | $0.04182 |
| Opus 5 | $0.00090 | $0.02091 |
| Sonnet 5 | $0.00036 | $0.00836 |
| Haiku 4.5 | $0.00018 | $0.00418 |
Grade A, and why
cite-placement 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cite-placement — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Citation Placement
Unified router for three citation workflows. A single Tkinter launcher collects
inputs and writes run_config.json; the "pipeline" value selects one of three
modes, each with its own detailed workflow document.
Modes and Routing
| Mode | pipeline value |
What it does | Workflow doc |
|---|---|---|---|
| Inline placement | inline |
Places screened citations as inline \cite{} / \citet{} / \citep{} commands with a compiled references.bib. For economics, finance, and social-science journals (APA, MLA, Harvard, Chicago author-date, IEEE, Vancouver). .tex only. |
references/phase-details-inline.md |
| Footnote placement | footnotes |
Places screened citations as full formatted \footnote{} (LaTeX) or native OOXML footnotes (Word), with one-click legal/notes style selection (Bluebook, OSCOLA, Chicago notes-bib, APA 7th, McGill) and Id./supra short-form post-processing. .tex or .docx. |
references/phase-details-footnotes.md |
| Restyle | restyle |
Converts ALL existing footnote citations (hand-written or pipeline-placed) from one style to another. No spreadsheet required. .tex or .docx. |
Restyle Pipeline section of references/phase-details-footnotes.md |
Read the relevant workflow document at the start of each phase.
Launcher-First Protocol
When the user triggers this skill:
- Run the launcher with a 10-minute timeout (the user needs time to browse
and configure), using the skill's known absolute directory as
[skill-dir], not the current working directory:
Call it via the Bash tool withpython "[skill-dir]/scripts/launcher.py"timeout: 600000. - The unified GUI presents the file fields and options for all three modes and
offers three run buttons — Inline Placement, Footnote Placement, and
Restyle — plus a Utilities area (Strip All Citations; Regenerate /
Reorder Cross-Refs, with or without an existing registry). On any run button
the launcher validates inputs and writes
placement/run_config.jsonin the output file's parent directory, then prints machine-readable status lines to stdout. - Parse the launcher's stdout:
LAUNCHER_STATUS: success— proceed. If missing orcancelled, stop.LAUNCHER_CONFIG_PATH: <path>— the absolute path torun_config.json. Use this path for all subsequent phases. All paths inside the config are absolute; do not assume the config lives in the current working directory.
- Read
run_config.jsonand route onconfig["pipeline"]:"inline"→ run the inline placement pipeline (references/phase-details-inline.md)."footnotes"→ run the footnote placement pipeline (references/phase-details-footnotes.md)."restyle"→ run the restyle pipeline (Restyle Pipeline section ofreferences/phase-details-footnotes.md).
- Run the selected pipeline end-to-end without asking questions or waiting for
confirmation between phases. The only pause is the Phase 4 human-in-the-loop
gate in the two placement modes, and only when
auto_approveisfalse.
What ships with it
43 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.
- README.md 13 KB
- references/phase-details-footnotes.md 70 KB
- references/phase-details-inline.md 52 KB
- references/styles/apa.json 825 B
- references/styles/apa.md 4.4 KB
- references/styles/bluebook.json 1.0 KB
- references/styles/bluebook.md 4.2 KB
- references/styles/chicago.json 914 B
- references/styles/chicago.md 3.5 KB
- references/styles/mcgill.json 1.0 KB
- references/styles/mcgill.md 4.3 KB
- references/styles/oscola.json 875 B
- references/styles/oscola.md 4.1 KB
- requirements-docx.txt 189 B
- scripts/core/__init__.py 0 B runs code
- scripts/core/docx_support/__init__.py 143 B runs code
- scripts/core/docx_support/audit_ooxml.py 3.8 KB runs code
- scripts/core/docx_support/converter.py 7.8 KB runs code
- scripts/core/docx_support/extract_text.py 5.4 KB runs code
- scripts/core/docx_support/footnotes.py 27 KB runs code
- scripts/core/docx_support/models.py 315 B runs code
- scripts/core/ingest_citations.py 18 KB runs code
- scripts/core/verify_citations.py 30 KB runs code
- scripts/docx_restyle.py 21 KB runs code
- scripts/launcher.py 23 KB runs code
- scripts/merge_adjacent_footnotes.py 10 KB runs code
- scripts/migrate_markers.py 3.2 KB runs code
- scripts/reorder_crossrefs.py 14 KB runs code
- scripts/short_form.py 35 KB runs code
- scripts/strip_citations.py 3.4 KB runs code
- scripts/tex_restyle.py 8.7 KB runs code
- tests/docx-restyle-test/conftest.py 835 B runs code
- tests/docx-restyle-test/input.docx 36 KB
- tests/docx-restyle-test/make_fixture.py 5.5 KB runs code
- tests/docx-restyle-test/test_extract.py 3.1 KB runs code
- tests/docx-restyle-test/test_insert.py 2.4 KB runs code
- tests/test_core_ingest_verify.py 9.9 KB runs code
- tests/test_merge_styles.py 2.8 KB runs code
- tests/test_short_form_styles.py 4.0 KB runs code
- tools/cite-restyle/build.bat 630 B runs code
- tools/cite-restyle/Citation Restyle Tool.spec 839 B
- tools/cite-restyle/README-dist.txt 3.8 KB
- tools/cite-restyle/restyle_app.py 17 KB runs code
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.
- 11d ago First seen · 257 lines · 181 tokens per session scan A 855cb1862d92
cite-placement is a skill published in the GitHub repository kennethkhoocy/applied-micro-skills (28 stars, last pushed 6d ago), licensed MIT. It adds 181 tokens to every session and 4,182 once invoked, about $0.0009 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
literature-searcher
Search CrossRef, OpenAlex, PubMed, Semantic Scholar, and optional Scopus; deduplicate results, download open-access PDFs by DOI, classify papers, monitor new results, and analyze coverage. Use when asked to search literature, monitor a topic, download an open-access paper, classify papers, or analyze literature gaps.
ccdb
A lookup tool for Carbonstop's CCDB, a database of carbon-emission factors for activities and materials. It supports checking factors by region and year and comparing their units, boundaries, specifications, and sources.
ieee-letter
Write or compress an IEEE communications LETTER for WCL (IEEE Wireless Communications Letters) or CL (IEEE Communications Letters): a single-contribution paper with a compressed introduction, no standalone related-work section, one system model, one core result (an algorithm OR a closed-form expression), and a tight…
ieee-experiments
Design and audit IEEE communications simulation and numerical-results sections for JSAC, TWC, TCOM, WCL, and CL. Covers benchmark schemes, Monte-Carlo protocol, BER/SER/outage/rate/EE metrics, SNR/antenna/user sweeps, analysis-vs-simulation validation, convergence and complexity, learning-based evaluation, ISAC…
ieee-polishing
Polish academic prose to IEEE-journal style at the sentence level — clarity, sentence length, section-appropriate tense, calibrated hedging, US English, acronym discipline, numbered-citation phrasing, and unit/number formatting. Also translate Chinese drafts into IEEE-style English. Use this whenever the user wants to…
ieee-response
Draft the two letters an IEEE submission needs — the point-by-point response to reviewers and the cover letter to the editor — so every comment is answered, every change is traceable to the revised manuscript, and the tone stays cooperative without conceding more than the evidence requires. Use this whenever the user…