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/Jamie-BitFlight/claude_skillsnpx agentmods add agents/jamie-bitflight/claude_skills/research-backlink-detectorWrote 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/jamie-bitflight/claude_skills/research-backlink-detector)<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/research-backlink-detector"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-backlink-detector/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/jamie-bitflight/claude_skills/research-backlink-detector"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/research-backlink-detector.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 | $0.00073 | $0.01575 |
| Opus 5 | $0.00036 | $0.00788 |
| Sonnet 5 | $0.00015 | $0.00315 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
research-backlink-detector 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Backlink Detector
Reads the ## Cross-References section of a target research entry, identifies each cited
entry, and appends a reciprocal backlink row to those cited entries. Ensures the
cross-reference graph is bidirectionally consistent after the research-cross-referencer
post-pass.
Input (from orchestrator prompt):
Add backlinks for ./research/{category}/{name}.md
Output: Each cited entry is edited to include a reciprocal backlink row pointing back to the target entry. The target entry itself is never modified.
Workflow
flowchart TD
Start([Receive target entry path]) --> ReadTarget[Read the full target entry file]
ReadTarget --> ParseRefs[Parse Cross-References table using backlink_lib.py<br>parse_cross_references_table]
ParseRefs --> AnyRefs{Any cross-reference rows found?}
AnyRefs -->|No rows| Done(["Return STATUS: complete<br>BACKLINKS_ADDED: 0<br>ENTRIES_MODIFIED: none<br>SKIPPED: none"])
AnyRefs -->|Rows present| ForEach[For each cited entry row]
ForEach --> ResolvePath[Resolve cited entry path via<br>backlink_lib.py resolve_link_path]
ResolvePath --> PathExists{Does the resolved path exist on disk?}
PathExists -->|No — dangling link| SkipDangling["Skip this entry<br>Record in SKIPPED with reason 'path not found'"]
SkipDangling --> NextRow[Next row]
PathExists -->|Yes| ReadCited[Read cited entry file]
ReadCited --> IdempotencyCheck[Check backlink_exists via backlink_lib.py<br>using normalized source link path]
IdempotencyCheck -->|Already present| SkipDup["Skip this entry<br>Record in SKIPPED with reason 'already exists'"]
SkipDup --> NextRow
IdempotencyCheck -->|Not present| Transform[Transform forward description to backlink<br>description via backlink_lib.py<br>transform_to_backlink_description]
Transform --> BuildRow[Build CrossRefRow with:<br>entry_name = source entry display name<br>link_path = relative path from cited entry to source entry<br>category = source category<br>relationship = transformed description]
BuildRow --> Append[Append row via backlink_lib.py<br>append_backlink_row]
Append --> WriteFile[Write updated cited entry to disk]
WriteFile --> RecordAdded[Record BACKLINKS_ADDED += 1<br>Record cited path in ENTRIES_MODIFIED]
RecordAdded --> NextRow
NextRow -->|More rows| ForEach
NextRow -->|All rows processed| Return([Return structured result block])
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 · 151 lines · 73 tokens per session scan A d65d06c807cc
research-backlink-detector is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,575 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.