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 mshadmanrahman/pm-pilot --skill manifest-readergit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/mshadmanrahman/pm-pilot/manifest-reader)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/manifest-reader"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/manifest-reader.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00010 | $0.00490 |
| Opus 5 | $0.00005 | $0.00245 |
| Sonnet 5 | $0.00002 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
manifest-reader 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 8d 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
Manifest Reader
Aggregate and summarize results from sub-agent manifest files.
When to Use
- After orchestrator completes a wave
- Reviewing results from parallel agent runs
- Session recap to see what was accomplished
- Debugging why a sub-agent produced unexpected results
Procedure
-
Locate Manifests
- Read all files in
.claude/manifests/ - Sort by modification time (newest first)
- Filter by session or task prefix if specified
- Read all files in
-
Parse Each Manifest Extract from frontmatter:
task: what was assignedstatus: complete, failed, partialagent: which agent ran it
Extract from body:
- Key findings
- Errors encountered
- Files created or modified
-
Aggregate
- Count: total, complete, failed, partial
- Group findings by theme or category
- Collect all errors into a single list
-
Summarize Output concise report:
Manifests: {count} found Status: {complete}/{total} complete, {failed} failed Key Findings: - {finding 1} - {finding 2} Errors: - {error 1 or "none"} Files Modified: - {path list}
Output Format
Manifests: 5 found
Status: 4/5 complete, 1 failed
Key Findings:
- Auth module has 3 unpatched vulnerabilities
- API coverage at 72%, below 80% target
- Database queries optimized (avg 40ms reduction)
Errors:
- security-scan: timeout after 120s on legacy module
Files Modified:
- src/api/users.ts
- src/db/queries.ts
Rules
- Read all manifests before summarizing (do not stream partial results)
- Highlight failures prominently
- Keep summary under 20 lines
- If no manifests found, say so clearly
- Do not delete manifests; the orchestrator handles cleanup
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.
- 8d ago First seen · 89 lines · 10 tokens per session scan A 89ac333c9157
manifest-reader is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 490 once invoked, about $0.0001 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
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
lat-md-knowledge-graph
Design or audit a repo-local markdown knowledge graph with wiki links, source-code backlinks, drift checks, and searchable sections. Use when AGENTS.md/CLAUDE.md is too flat for a large codebase or when a custom harness needs durable structured project memory.
build-implementation
Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".