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 agentmods add commands/andrefigueira/.context/score-context-testgit clone --depth 1 https://github.com/andrefigueira/.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/commands/andrefigueira/.context/score-context-test)<a href="https://agentmods.dev/commands/andrefigueira/.context/score-context-test"><img src="https://agentmods.dev/badge/commands/andrefigueira/.context/score-context-test.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00381 |
| Opus 5 | $0.00000 | $0.00191 |
| Sonnet 5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
score-context-test 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 6d 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.
What it actually says
You are scoring a test output for the .context vs CLAUDE.md comparison study.
Test to Score
Arguments: $ARGUMENTS (e.g., "01-simple-endpoint control run-1704067200000")
Parse to get: case_id, group, run_id
Instructions
-
Load the test case from
tests/cases/{case_id}.md- get expected behaviors and scoring criteria -
Load the output from
tests/outputs/{case_id}/{group}/{run_id}.md -
Load the rubrics from
tests/rubrics/:- pattern-adherence.md
- completeness.md
- correctness.md
- security.md
- consistency.md
-
Score the output against each dimension (0-10)
-
Save scores to
tests/results/scores/{case_id}/{group}/{run_id}-scores.json
Use this JSON format:
{
"case_id": "...",
"group": "...",
"run_id": "...",
"scores": {
"pattern_adherence": { "score": X, "notes": "...", "deductions": [] },
"completeness": { "score": X, "notes": "...", "deductions": [] },
"correctness": { "score": X, "notes": "...", "deductions": [] },
"security": { "score": X, "notes": "...", "deductions": [] },
"consistency": { "score": X, "notes": "...", "deductions": [] }
},
"total": X
}
Scoring Guidelines
- Be objective and consistent
- Apply deductions as specified in rubrics
- Note specific examples supporting your scores
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.
- 6d ago First seen · 48 lines · 0 tokens per session scan A 63a9fd77e81e
score-context-test is a command published in the GitHub repository andrefigueira/.context (253 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 381 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.