Anji Xu's open-source Claude Statuspane puts context use, five-hour and seven-day rate limits and session cost in a card above the Claude Code prompt. The readout lives on that one developer's screen, so whoever answers for a team's total agent spend still needs records kept somewhere central.
Reality
- Evidence45
- Adoption5
- Hype gap0
- Incentives
- Insufficient
- Confidence50
Glow says AI coding agents asked for review screenshots put over 13,000 internal images from 300-plus organizations into public GitHub repositories. Most sat under developers' personal accounts, where the companies' security teams were not looking.
Perspective Coverage
5 publishers
- Builder
- Builder 37%
- Operator
- Operator 53%
- Investor
- Investor 10%
Reality
- Evidence55
- Adoption45
- Hype gap+15
- Incentives70
- Confidence60
One developer's free static host sent HTTP 429 to every visitor after a daily visit quota ran out, while its deploy API still reported the release ready. Both green signals, deploy status and a scripted check, missed a ceiling that sat on the serving path.
Reality
- Evidence50
- Adoption
- Insufficient
- Hype gap+5
- Incentives
- Insufficient
- Confidence45
Glow's PixelLeak report found coding agents exposed more than 13,000 private screenshots from over 300 organisations by hosting them in public GitHub repos. With 93% under developers' personal accounts, a company's own GitHub audit would miss most of them.
Perspective Coverage
3 publishers
- Builder
- Builder 42%
- Operator
- Operator 50%
- Investor
- Investor 8%
Reality
- Evidence55
- Adoption50
- Hype gap+10
- Incentives55
- Confidence60
One developer's weekly Claude Code skill update failed on 6, 13 and 20 September despite three layered fixes and an audit note reading "exit 0". The script caught and logged every failure correctly, but the log had no reader until the author opened it after the third one.
Reality
- Evidence55
- Adoption
- Insufficient
- Hype gap+10
- Incentives
- Insufficient
- Confidence55
The failure landed on artifact upload, weeks after the pipeline went stable. The audit found ten near-identical Gradle caches, one per active branch, a hashFiles key that never matched anything, and 30-day retention on 70MB builds.
Reality
- Evidence60
- Adoption20
- Hype gap+12
- Incentives30
- Confidence55
On a self-hosted spot runner, an instance AWS reclaimed and a genuinely broken test both produce the same red X, so this pipeline reads the raw job log for four host-only strings and re-runs only the jobs the host killed.
Reality
- Evidence64
- Adoption10
- Hype gap−10
- Incentives18
- Confidence58
The watchdog's own death and its one true alert both surface as step 6 failing, so three nights of verifying nothing look identical to the night it caught a daily cron that had been dead for 70.4 days.
Reality
- Evidence72
- Adoption15
- Hype gap+8
- Incentives22
- Confidence58
Enforcement is a bash script that counts files against the merge-base with the parent branch, so it bounds one diff at a time, and only if the agent chooses to run it. The 100 is an environment variable's default.
Reality
- Evidence58
- Adoption
- Insufficient
- Hype gap+35
- Incentives
- Insufficient
- Confidence62
Permission rules accumulate from "yes, don't ask again" answers into a repo-local file, and because matching runs deny then ask then allow with no specificity tiebreak, a policy that reads correctly can still stall an unattended run.
Reality
- Evidence55
- Adoption22
- Hype gap+8
- Incentives32
- Confidence58
Stacked pull requests are still in public preview, and the command that creates them is not the command that updates them. What the extension does remove is the author-side coordination cost that made "make your diffs smaller" an argument rather than a workflow.
Reality
- Evidence46
- Adoption18
- Hype gap+15
- Incentives42
- Confidence47
A desktop app that shells out to openssl.exe and ffmpeg.exe can absorb a CVE with a few-megabyte drop-in. The author is unusually clear about the price: spawn latency, and a parser per tool.
Reality
- Evidence30
- Adoption20
- Hype gap+5
- Incentives65
- Confidence48
A Mac utility replaces plaintext credentials with fake ones and injects the real value into an approved process after Touch ID. The pattern is now on every security team's evaluation list.
Reality
- Evidence36
- Adoption9
- Hype gap+28
- Incentives68
- Confidence38
A solo founder says every rule in his agent system was written after a failure, and that only shell-level blocks held. The interesting part is the promotion threshold, not the count.
Reality
- Evidence26
- Adoption12
- Hype gap+28
- Incentives68
- Confidence34