Skills/ClawHub/cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction

cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction@6.0.0

VERIFIED· install only

Publisher claims: "Claw Compactor v6.0 — 50%+ savings through rule-based compression, dictionary encoding, session observation compression, and progressive context loading." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher aeromomo · publishing for 285 daysInstalls 2,677Last detonated 1 h ago
$clawhub install cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 17 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction@6.0.0 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: audit_memory.py: error: the following arguments are required: workspace
0.1sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: compress_memory.py: error: the following arguments are required: path
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: compressed_context.py: error: the following arguments are required: file
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 2: dedup_memory.py: error: the following arguments are required: path
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 2: dictionary_compress.py: error: the following arguments are required: workspace
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 2: estimate_tokens.py: error: the following arguments are required: path
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 2: generate_summary_tiers.py: error: the following arguments are required: path
0.8sprocessbundled script run in the sandbox with no arguments
0.9sprocessexited 2: mem_compress.py: error: the following arguments are required: workspace, command
0.9sprocess8 of 17 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.9sprocessscript backend runs setup only
0.9sprocessscript backend runs setup only
0.9sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedtests/test_cli_commands.py:215 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_cli_commands.py:15 · Python subprocess execution detectedresult = subprocess.run(args, capture_output=True, text=True, timeout=timeout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_tokenizer_optimizer.py:163 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestext = """## SSH 密钥 (在 ~/.ssh/)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_integration.py:203 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_cli_commands.py:221 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_cli_commands.py:208 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_lib_markdown.py:220 · Hidden zero-width characters detected — may conceal contenttext = "test 👨‍👩‍👧‍👦 end"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07

Cost to the agent

Instructions loaded
≈1,824 tok
1 file · 65 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction@6.0.0 safety verdict: Verified (install only) — KillerSkills